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

    Neuronpedia

    INDEX
    Explanations

    digits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     contribution
    -0.07
    ocrats
    -0.06
    ufacturer
    -0.06
    들이
    -0.06
    _lane
    -0.06
    ları
    -0.06
    agas
    -0.06
    yah
    -0.06
    ederal
    -0.06
    ASN
    -0.06
    POSITIVE LOGITS
     Observation
    0.07
    .ra
    0.06
    (help
    0.06
    .:.
    0.06
     مدت
    0.06
    .setLayout
    0.06
    _check
    0.06
    .setHeight
    0.06
    _upd
    0.06
    LIC
    0.06
    Act Density 0.014%

    No Known Activations