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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     TimeZone
    -0.07
     incap
    -0.06
     regard
    -0.06
     UserControl
    -0.06
    널
    -0.06
    .unknown
    -0.06
     scram
    -0.06
     причин
    -0.06
    Burn
    -0.06
     grains
    -0.06
    POSITIVE LOGITS
    orses
    0.06
     Clarke
    0.06
     yüksel
    0.06
     Bison
    0.06
     praising
    0.06
    .getDescription
    0.06
    ultimo
    0.06
    ीक
    0.06
    .Secret
    0.06
     витами
    0.06
    Act Density 0.023%

    No Known Activations