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

    Neuronpedia

    INDEX
    Explanations

    type

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    任命
    -0.07
    㢨
    -0.07
     kaç
    -0.07
    👦
    -0.07
     errores
    -0.07
     unterstützen
    -0.07
     suma
    -0.07
    ℇ
    -0.07
    _Sh
    -0.07
    _SE
    -0.06
    POSITIVE LOGITS
    ic
    0.07
    imps
    0.07
    ⋯
    0.07
    	time
    0.07
    moid
    0.06
    处理
    0.06
    .fs
    0.06
    _book
    0.06
    近代
    0.06
    .Italic
    0.06
    Act Density 0.001%

    No Known Activations