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

    Neuronpedia

    INDEX
    Explanations

    discipline and punishment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     It
    0.50
     Marc
    0.48
     M
    0.48
     Mark
    0.48
     Madness
    0.48
     Chryst
    0.48
    thumb
    0.46
     Sun
    0.46
     Marks
    0.46
     अमिताभ
    0.46
    POSITIVE LOGITS
    ເຄ
    0.48
    PRIVATE
    0.46
    phenoxymethyl
    0.46
     הם
    0.46
    ேத்க
    0.46
    zaXR
    0.46
     څنګه
    0.45
    equivariant
    0.44
    DEPLOY
    0.44
     любы
    0.44
    Act Density 0.016%

    No Known Activations