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

    Neuronpedia

    INDEX
    Explanations

    skyline followed by view or location

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    け
    1.33
    ва
    1.31
    ב
    1.22
    يف
    1.20
    ба
    1.19
    ון
    1.17
    いた
    1.13
    ור
    1.11
    са
    1.10
    padă
    1.09
    POSITIVE LOGITS
    il
    1.19
     \
    1.18
     I
    1.17
    are
    1.12
    ak
    1.09
    u
    1.09
    ang
    1.05
    1.04
    s
    1.04
    uk
    1.02
    Act Density 0.000%

    No Known Activations