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

    Neuronpedia

    INDEX
    Explanations

    how it works

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     astray
    1.40
    д
    1.35
     perfeito
    1.28
     સ્વા
    1.27
     dotyczą
    1.26
     produz
    1.23
     mikä
    1.20
     потрібно
    1.18
    gesch
    1.17
     परिचय
    1.15
    POSITIVE LOGITS
    اً
    1.17
    ло
    1.14
    र
    1.14
    渟
    1.14
    ով
    1.14
    𝗸
    1.09
     vinegar
    1.08
    靂
    1.07
    ervation
    1.05
    ي
    1.04
    Act Density 0.262%

    No Known Activations