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

    Neuronpedia

    INDEX
    Explanations

    graphs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     maize
    -0.08
    known
    -0.08
     Joy
    -0.07
    _clusters
    -0.07
     Fant
    -0.07
    Metrics
    -0.06
     regained
    -0.06
    로나
    -0.06
     major
    -0.06
    ژن
    -0.06
    POSITIVE LOGITS
    -м
    0.08
    جر
    0.06
    -IS
    0.06
     senior
    0.06
    $wp
    0.06
    _List
    0.06
     кажд
    0.06
    0.06
    잡담
    0.06
    .FR
    0.06
    Act Density 0.001%

    No Known Activations