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

    Neuronpedia

    INDEX
    Explanations

    breakdown of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     whether
    0.96
     Whether
    0.86
     Any
    0.84
     Which
    0.83
    Which
    0.82
    Whether
    0.82
    Any
    0.82
     outline
    0.76
     list
    0.75
     any
    0.74
    POSITIVE LOGITS
    相当于
    0.95
     значения
    0.93
     konstant
    0.89
     emitida
    0.87
    lestage
    0.87
     acredita
    0.86
     denominations
    0.85
    時間が
    0.85
    ಡೆ
    0.85
    quando
    0.85
    Act Density 0.127%

    No Known Activations