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

    Neuronpedia

    INDEX
    Explanations

    om

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =Y
    -0.08
    _DROP
    -0.06
    098
    -0.06
     с
    -0.06
    ICC
    -0.06
    _ann
    -0.06
     ин
    -0.06
     Roy
    -0.06
     Rosenberg
    -0.06
     cabo
    -0.06
    POSITIVE LOGITS
    visit
    0.07
    .getProperties
    0.06
     British
    0.06
     dis
    0.06
     Ahmet
    0.06
    pered
    0.06
     facing
    0.06
     ti
    0.06
    kaç
    0.06
    .IsActive
    0.06
    Act Density 0.097%

    No Known Activations