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

    Neuronpedia

    INDEX
    Explanations

    integrate front-end

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rupani
    0.47
     dll
    0.46
    스러
    0.45
    定理
    0.43
    蹦
    0.42
     racemic
    0.42
     časti
    0.42
    ㄾ
    0.42
     கடும்
    0.41
     dune
    0.41
    POSITIVE LOGITS
     S
    0.43
     so
    0.41
    conc
    0.40
    Print
    0.38
    DICTION
    0.38
     Conc
    0.37
     supp
    0.36
    action
    0.35
    Tah
    0.35
     Forrest
    0.35
    Act Density 0.000%

    No Known Activations