Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    sections that discuss advantages or benefits in a context, particularly in academic or technical documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    sections discussing advantages and acknowledgments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    git diff

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Conclusions
    -0.62
     Administrativna
    -0.62
    ViewImports
    -0.61
    tanleria
    -0.61
    versial
    -0.60
    querque
    -0.60
    FormTagHelper
    -0.60
    lunda
    -0.57
     Summers
    -0.56
     Mathis
    -0.55
    POSITIVE LOGITS
    +:+
    0.78
    CppCodeGen
    0.60
    EndInit
    0.56
     saites
    0.51
    None
    0.51
     trifft
    0.50
     UIAlert
    0.50
    Kontra
    0.50
    DIPSETTING
    0.49
    BagLayout
    0.48
    Act Density 0.005%

    No Known Activations