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

    Neuronpedia

    INDEX
    Explanations

    articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ash
    -0.06
    (that
    -0.06
    -0.06
     Delicious
    -0.06
    .shuffle
    -0.06
    ždy
    -0.06
    |x
    -0.06
    olor
    -0.06
     Ling
    -0.06
    _kind
    -0.06
    POSITIVE LOGITS
    organisation
    0.07
     її
    0.07
     dirección
    0.06
    <Entity
    0.06
     behind
    0.06
    GN
    0.06
     condolences
    0.06
     tratt
    0.06
    ़े
    0.06
     Codable
    0.06
    Act Density 0.020%

    No Known Activations