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

    Neuronpedia

    INDEX
    Explanations

    compression

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tablet
    -0.07
    eeee
    -0.07
     ANAL
    -0.06
    zl
    -0.06
    .fhir
    -0.06
     υπό
    -0.06
    _fig
    -0.06
     ters
    -0.06
    slu
    -0.06
    .nasa
    -0.06
    POSITIVE LOGITS
     Gateway
    0.08
    -offs
    0.07
    Gateway
    0.07
     당시
    0.06
    abbage
    0.06
    (entities
    0.06
    作
    0.06
    isActive
    0.06
    simd
    0.06
    CAN
    0.06
    Act Density 0.015%

    No Known Activations