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

    Neuronpedia

    INDEX
    Explanations

    percent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     percent
    -0.88
     Percent
    -0.73
    percent
    -0.72
    Percent
    -0.71
    derry
    -0.62
    PERTIES
    -0.59
    stantial
    -0.59
    UMBIA
    -0.57
    ULDER
    -0.57
     percentage
    -0.57
    POSITIVE LOGITS
    esModule
    0.68
     ***!
    0.59
     subordination
    0.58
    ThroughAttribute
    0.57
    .
    0.57
     insolvency
    0.56
    )
    0.55
     morbidity
    0.54
    Composable
    0.54
    حياته
    0.53
    Act Density 0.073%

    No Known Activations