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

    Neuronpedia

    INDEX
    Explanations

    net

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    анг
    -0.07
     Creed
    -0.07
    耶
    -0.06
    モ
    -0.06
    з
    -0.06
     onResponse
    -0.06
    _EDGE
    -0.06
     dlouhodob
    -0.06
    orr
    -0.06
     sơ
    -0.06
    POSITIVE LOGITS
     '"
    0.07
    Diagnostic
    0.07
    Xi
    0.07
    'icon
    0.07
     glacier
    0.07
    Shutdown
    0.07
    '´
    0.06
     newList
    0.06
     inhibitor
    0.06
    -time
    0.06
    Act Density 0.002%

    No Known Activations