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

    Neuronpedia

    INDEX
    Explanations

    time measurements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Iris
    -0.07
    ullah
    -0.06
    Clusters
    -0.06
    dock
    -0.06
    Button
    -0.06
     Dudley
    -0.06
     tumor
    -0.06
    rowing
    -0.06
     taxpayer
    -0.06
     getLogger
    -0.06
    POSITIVE LOGITS
    COND
    0.07
    urent
    0.07
     fractional
    0.07
    _ent
    0.07
     Değ
    0.06
    drž
    0.06
    _gc
    0.06
     compart
    0.06
    xy
    0.06
     Palest
    0.06
    Act Density 0.050%

    No Known Activations