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

    Neuronpedia

    INDEX
    Explanations

    prefix

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Indo
    -0.07
    Done
    -0.07
     boon
    -0.07
     建
    -0.06
     เห
    -0.06
    codile
    -0.06
    Canon
    -0.06
    noxious
    -0.06
    (Property
    -0.06
    -water
    -0.06
    POSITIVE LOGITS
    prefix
    0.23
    PREFIX
    0.11
    .prefix
    0.07
    _imag
    0.07
    (minutes
    0.07
    ('/:
    0.07
    .lab
    0.06
    buckets
    0.06
    .FileName
    0.06
     rankings
    0.06
    Act Density 0.002%

    No Known Activations