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

    Neuronpedia

    INDEX
    Explanations

    research studies focusing on medical or scientific investigations

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

    conclusions and findings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵↵
    -0.43
    <eos>
    -0.43
    ↵↵↵
    -0.42
     char
    -0.37
     Sa
    -0.37
     Hir
    -0.37
    ...
    -0.36
     Bur
    -0.35
     Ap
    -0.35
    ↵
    -0.35
    POSITIVE LOGITS
    AddTagHelper
    0.99
    Tikang
    0.77
    Personendaten
    0.76
     utafitiHapana
    0.73
    KURZBESCHREIBUNG
    0.71
    ReusableCell
    0.69
    RenderAtEndOf
    0.69
    WriteTagHelper
    0.68
    httphttps
    0.67
    évaluateur
    0.67
    Act Density 0.053%

    No Known Activations