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

    Neuronpedia

    INDEX
    Explanations

    the public

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    力的
    0.41
     infl
    0.38
    _{-}^{
    0.38
    耦
    0.35
    些
    0.35
    ఎస్
    0.34
    ලු
    0.34
    चारा
    0.34
    ót
    0.34
    uff
    0.33
    POSITIVE LOGITS
     public
    1.39
     Öffentlichkeit
    1.35
    public
    1.32
     público
    1.29
    公众
    1.25
     pubblico
    1.16
     veřej
    1.14
     públicas
    1.13
     publique
    1.13
     pública
    1.12
    Act Density 0.031%

    No Known Activations