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

    Neuronpedia

    INDEX
    Explanations

    making a contribution

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pero
    -0.07
    pagina
    -0.07
    跌
    -0.07
     навк
    -0.06
    .Headers
    -0.06
    絡
    -0.06
    Birthday
    -0.06
    áno
    -0.06
    μένοι
    -0.06
    _planes
    -0.06
    POSITIVE LOGITS
    .like
    0.07
     refined
    0.07
    .Down
    0.07
     мал
    0.06
    _render
    0.06
    _reader
    0.06
    tf
    0.06
    .Cap
    0.06
    paredStatement
    0.06
     contributions
    0.06
    Act Density 0.184%

    No Known Activations