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

    Neuronpedia

    INDEX
    Explanations

    towers and bells

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gas
    -0.07
     Reconstruction
    -0.07
    .tail
    -0.07
     Timer
    -0.07
     amounts
    -0.07
    stylesheet
    -0.06
    Machine
    -0.06
    war
    -0.06
    .gradient
    -0.06
     landscaping
    -0.06
    POSITIVE LOGITS
     tvb
    0.07
     Во
    0.06
    tras
    0.06
    .Att
    0.06
     هی
    0.06
    _RB
    0.06
     обязан
    0.06
     चलत
    0.06
    EDIATEK
    0.06
    _hop
    0.06
    Act Density 0.002%

    No Known Activations