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

    Neuronpedia

    INDEX
    Explanations

    categorieswaysbuiltpartsStartingthanobicwhois

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WeakTable
    1.30
    дение
    1.30
    ⿳
    1.26
    1.20
     unidos
    1.10
     ligados
    1.10
     灬
    1.09
     Harden
    1.09
     NgModule
    1.09
    тет
    1.08
    POSITIVE LOGITS
    le
    1.02
    G
    0.96
    C
    0.94
    ick
    0.93
    mathscr
    0.90
    MIS
    0.89
    TT
    0.85
    itt
    0.84
    res
    0.84
    RF
    0.83
    Act Density 0.000%

    No Known Activations