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

    Neuronpedia

    INDEX
    Explanations

    records of scores or numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sign
    -1.20
     signing
    -1.15
     Sign
    -1.11
    Sign
    -1.11
     only
    -0.99
     chose
    -0.92
     signed
    -0.91
    サイン
    -0.86
     Only
    -0.86
    签
    -0.85
    POSITIVE LOGITS
     monstruos
    1.05
    1.00
     superhuman
    0.98
     nudo
    0.98
    artements
    0.96
    brechen
    0.94
     voul
    0.94
     hoge
    0.93
    üstü
    0.93
    REME
    0.92
    Act Density 0.044%

    No Known Activations