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

    Neuronpedia

    INDEX
    Explanations

    registration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (nome
    -0.07
    (short
    -0.07
    чний
    -0.07
     CPP
    -0.07
    .norm
    -0.07
     dex
    -0.06
    uve
    -0.06
     presents
    -0.06
     predator
    -0.06
     بیان
    -0.06
    POSITIVE LOGITS
    =df
    0.07
    %)↵↵
    0.07
     yapı
    0.06
     ruled
    0.06
     assail
    0.06
     cavalry
    0.06
    ivated
    0.06
    ateř
    0.06
     motivated
    0.06
    :^{↵
    0.06
    Act Density 0.014%

    No Known Activations