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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Reynolds
    -0.07
     cloud
    -0.07
    193
    -0.07
     Wright
    -0.06
     Typed
    -0.06
     fila
    -0.06
    ency
    -0.06
     Lowest
    -0.06
     Fukushima
    -0.06
     desert
    -0.06
    POSITIVE LOGITS
    #undef
    0.06
    (random
    0.06
    غات
    0.06
    =min
    0.06
    _COLL
    0.06
     ____
    0.06
    数学
    0.06
    avery
    0.06
    :end
    0.06
    .randint
    0.06
    Act Density 0.057%

    No Known Activations