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

    Neuronpedia

    INDEX
    Explanations

    component

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     components
    -1.71
     component
    -1.70
    components
    -1.60
     Components
    -1.52
    Components
    -1.48
    component
    -1.43
     Component
    -1.36
    Component
    -1.28
     COMPONENTS
    -1.24
     componentes
    -1.23
    POSITIVE LOGITS
     Efq
    0.84
     uſed
    0.84
     myſelf
    0.81
     Monfieur
    0.76
     whoſe
    0.74
     flocc
    0.74
     Résultats
    0.74
     ſaid
    0.73
    TypedDataSet
    0.73
     himſelf
    0.72
    Act Density 0.275%

    No Known Activations