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

    Neuronpedia

    INDEX
    Explanations

    cat

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aient
    1.16
    т
    1.11
    р
    1.11
    いる
    1.09
    ますが
    1.09
    िल
    1.08
    ર
    1.07
    DE
    1.06
    ರೆ
    1.06
    बी
    1.05
    POSITIVE LOGITS
    슨
    1.20
     tenets
    1.14
    ar
    1.13
    loid
    1.12
    kali
    1.12
    boxyl
    1.10
    ại
    1.08
    fois
    1.05
    stown
    1.05
    ad
    1.04
    Act Density 0.117%

    No Known Activations