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

    Neuronpedia

    INDEX
    Explanations

    is or not

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Allan
    -0.07
     Dare
    -0.06
     Jah
    -0.06
     Voyager
    -0.06
     Preston
    -0.06
     Dion
    -0.06
    Kent
    -0.06
    %,
    -0.06
    .header
    -0.06
     Kent
    -0.06
    POSITIVE LOGITS
     LIC
    0.07
     tutte
    0.07
     nebu
    0.07
    -Apr
    0.06
    萬
    0.06
     PATCH
    0.06
    .HTTP
    0.06
     вищ
    0.06
    licher
    0.06
    SUR
    0.06
    Act Density 0.147%

    No Known Activations