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

    Neuronpedia

    INDEX
    Explanations

    Japanese programming questions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ฃ
    -0.07
    胝
    -0.07
     الحكم
    -0.07
    /modules
    -0.07
    USED
    -0.07
    .Undef
    -0.07
    ileged
    -0.07
     Raz
    -0.07
    �ん
    -0.06
    Deferred
    -0.06
    POSITIVE LOGITS
     "";↵↵
    0.08
    .volume
    0.07
     ben
    0.07
     cele
    0.07
    ניוזלטר
    0.07
    Home
    0.07
    (vo
    0.07
     Verification
    0.07
    mary
    0.06
     FC
    0.06
    Act Density 0.042%

    No Known Activations