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

    Neuronpedia

    INDEX
    Explanations

    rough visual approximation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     políticas
    0.47
     पॉलिसी
    0.46
    riminal
    0.46
    並不
    0.44
    🗽
    0.44
    un
    0.43
     Policies
    0.43
     politiche
    0.42
    ുകയാണ്
    0.42
     IMHO
    0.42
    POSITIVE LOGITS
    粗
    0.47
     rough
    0.47
     干
    0.45
     ξ
    0.44
     TInner
    0.43
     Dirac
    0.42
     miss
    0.42
     కోసం
    0.42
     more
    0.42
     mih
    0.42
    Act Density 0.000%

    No Known Activations