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

    Neuronpedia

    INDEX
    Explanations

    geopolitical conflicts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    httphttps
    -0.59
     informée
    -0.57
     anhyd
    -0.57
    inheritDoc
    -0.52
     ribos
    -0.51
     desierto
    -0.50
     AppModule
    -0.49
     Waray
    -0.48
    wenden
    -0.48
    Français
    -0.48
    POSITIVE LOGITS
     HAM
    0.53
    oneofs
    0.53
     useStyles
    0.53
     Hame
    0.52
    AttributeSet
    0.50
     estekak
    0.50
    OptionsMenu
    0.50
    Ham
    0.48
     getItemId
    0.48
     H
    0.47
    Act Density 0.002%

    No Known Activations