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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    렁
    -0.07
     Bailey
    -0.07
    	ev
    -0.07
    呼和
    -0.06
     resembl
    -0.06
    Cs
    -0.06
    oman
    -0.06
     trench
    -0.06
     Walker
    -0.06
     Tanner
    -0.06
    POSITIVE LOGITS
     studying
    0.09
     כיום
    0.07
    ＊
    0.07
    (ui
    0.07
     syntax
    0.07
    菲律
    0.07
     zoning
    0.07
    (*)(
    0.07
    _literals
    0.07
    สะดวก
    0.07
    Act Density 0.001%

    No Known Activations