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

    Neuronpedia

    INDEX
    Explanations

    definitions and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    EMPLOY
    1.26
    Grid
    1.24
     เช่น
    1.22
    ૂર્ણ
    1.21
    س
    1.21
    InitStruct
    1.20
    お客
    1.20
    あるいは
    1.19
     MACHINERY
    1.16
     इंस्ट
    1.16
    POSITIVE LOGITS
    t
    1.48
    ak
    1.39
    ik
    1.27
    etin
    1.23
    ни
    1.22
    ायचे
    1.18
     habido
    1.11
    ethanol
    1.09
    牠
    1.09
    am
    1.08
    Act Density 0.000%

    No Known Activations