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

    Neuronpedia

    INDEX
    Explanations

    official documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aş
    -0.06
    _AREA
    -0.06
    -income
    -0.06
     Kos
    -0.06
    .Power
    -0.06
    ी,
    -0.05
     earm
    -0.05
     endorsed
    -0.05
     Herz
    -0.05
     yc
    -0.05
    POSITIVE LOGITS
     thermometer
    0.07
    experimental
    0.07
     cleanliness
    0.07
    adx
    0.07
    lice
    0.07
     capturing
    0.06
    toggle
    0.06
    -ajax
    0.06
     UILabel
    0.06
     "#"
    0.06
    Act Density 0.007%

    No Known Activations