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

    Neuronpedia

    INDEX
    Explanations

    class definitions and functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ة
    2.59
    lt
    2.31
    me
    2.27
    ne
    2.25
    ת
    2.09
    or
    2.08
     hí
    2.07
    politik
    2.07
    اً
    2.04
    an
    2.04
    POSITIVE LOGITS
    2.21
    ➢
    2.21
    2.12
    2.11
    uleiro
    2.10
    ங்கிணை
    2.07
    2.06
    ❯
    2.03
    гант
    2.03
    安心して
    2.01
    Act Density 0.001%

    No Known Activations