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

    Neuronpedia

    INDEX
    Explanations

    66

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ີນ
    0.79
    𝙣
    0.78
     Take
    0.77
    EN
    0.76
     compless
    0.76
    𝗻
    0.69
    Take
    0.68
     getN
    0.68
    シーズン
    0.67
    ंठ
    0.67
    POSITIVE LOGITS
     जबाब
    0.56
    レンダー
    0.52
    申报
    0.51
     ubiquitin
    0.48
    rpc
    0.48
     cross
    0.48
    mult
    0.48
     crosses
    0.47
    owicz
    0.47
     descending
    0.47
    Act Density 0.221%

    No Known Activations