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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     
    -0.56
    ↵↵↵
    -0.50
    ↵↵
    -0.50
    TITUDE
    -0.48
    сив
    -0.48
     c
    -0.47
    -
    -0.47
     imagining
    -0.47
     En
    -0.46
     asking
    -0.46
    POSITIVE LOGITS
    ScopeManager
    0.93
     purpoſe
    0.92
     createState
    0.90
    DeleteBehavior
    0.88
     itſelf
    0.86
     uſed
    0.84
    uxxxx
    0.83
     themſelves
    0.83
     pleaſure
    0.82
     reaſon
    0.81
    Act Density 0.018%

    No Known Activations