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

    Neuronpedia

    INDEX
    Explanations

    worth living or considering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    此之外
    1.36
    てください
    1.34
     '\''
    1.20
     Pratap
    1.20
    най
    1.15
     corroborate
    1.15
     chances
    1.15
    indicate
    1.15
     hailed
    1.14
     opcoes
    1.14
    POSITIVE LOGITS
    ر
    1.61
    𝒾
    1.54
    러
    1.52
    紝
    1.50
    лната
    1.50
    𝒶
    1.43
     परीक्षा
    1.42
    Од
    1.42
    ᅨ
    1.39
     troca
    1.38
    Act Density 0.022%

    No Known Activations