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

    Neuronpedia

    INDEX
    Explanations

    seven

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    敏
    -0.07
     Agility
    -0.07
    іть
    -0.06
    μενο
    -0.06
    jpg
    -0.06
     дерева
    -0.06
    (ray
    -0.06
    ёл
    -0.06
    _feed
    -0.06
     angered
    -0.06
    POSITIVE LOGITS
    .iloc
    0.07
    dispose
    0.06
     bara
    0.06
    (status
    0.06
    .Assembly
    0.06
    atown
    0.06
    vetica
    0.06
    protobuf
    0.06
    наслід
    0.06
    .authenticate
    0.06
    Act Density 0.000%

    No Known Activations