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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tru
    -0.07
    付け
    -0.07
     созда
    -0.06
    ера
    -0.06
     furniture
    -0.06
     Bölgesi
    -0.06
     backgrounds
    -0.06
    undos
    -0.06
     Obama
    -0.06
     Saw
    -0.06
    POSITIVE LOGITS
    luent
    0.07
     originating
    0.06
    	GLuint
    0.06
    ПК
    0.06
    .Wh
    0.06
    _bool
    0.06
    rtle
    0.06
     oe
    0.06
    =[],
    0.06
    _OM
    0.06
    Act Density 0.033%

    No Known Activations