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

    Neuronpedia

    INDEX
    Explanations

    definition and explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     기타
    0.37
    гель
    0.36
    䔧
    0.34
     систем
    0.33
     япон
    0.33
    荭
    0.32
     hulle
    0.32
     норма
    0.32
     рекоменда
    0.32
     других
    0.32
    POSITIVE LOGITS
    也
    0.46
    之所以
    0.44
    只是
    0.42
    は
    0.41
     only
    0.41
    是
    0.38
    的主
    0.38
     also
    0.38
    也有
    0.37
     is
    0.37
    Act Density 0.014%

    No Known Activations