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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     perfectly
    -0.07
     women
    -0.07
     sobre
    -0.06
    215
    -0.06
     lords
    -0.06
     waiting
    -0.06
     anyways
    -0.06
    앙
    -0.06
    expects
    -0.06
     ropes
    -0.06
    POSITIVE LOGITS
    :'',
    0.07
    .path
    0.07
    keyCode
    0.06
     formatDate
    0.06
    เธอ
    0.06
     노출등록
    0.06
    _unpack
    0.06
    探
    0.06
    ोद
    0.06
    _STREAM
    0.06
    Act Density 0.085%

    No Known Activations