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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to systems and processes

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

    results in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     GenerationType
    -0.49
     geométrico
    -0.41
     لينك
    -0.40
    पया
    -0.40
    WebElementEntity
    -0.40
     nonUne
    -0.39
    BufferException
    -0.39
    featureID
    -0.38
    lorette
    -0.37
     TextAppearance
    -0.35
    POSITIVE LOGITS
    colhead
    0.41
     inför
    0.39
    Derbyniad
    0.38
    dorff
    0.37
    arXiv
    0.37
    RTEX
    0.36
     prospective
    0.36
    HandleFunc
    0.36
    Datuak
    0.36
    zczy
    0.36
    Act Density 0.267%

    No Known Activations