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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Once
    -0.07
     readOnly
    -0.07
    Any
    -0.07
    .Any
    -0.07
    .TestCase
    -0.06
     offences
    -0.06
     traffic
    -0.06
    Just
    -0.06
    Mp
    -0.06
    otherwise
    -0.06
    POSITIVE LOGITS
    、や
    0.07
    threshold
    0.06
     बढ़
    0.06
    .COL
    0.06
    átor
    0.06
     복
    0.06
    ):
    0.06
    `='$
    0.06
     extrav
    0.06
     Ski
    0.06
    Act Density 0.107%

    No Known Activations