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

    Neuronpedia

    INDEX
    Explanations

    instances of someone being forcefully removed or told to leave

    oai_token-act-pair · gemini-2.0-flash

    say "removal"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     exit
    -1.17
     exiting
    -1.07
     exits
    -1.06
     Exit
    -1.03
    exit
    -1.02
    Exit
    -0.98
     departure
    -0.96
    Exiting
    -0.91
    EXIT
    -0.88
     departures
    -0.87
    POSITIVE LOGITS
    WriteBarrier
    0.87
    Personendaten
    0.86
     jScrollPane
    0.78
    providedIn
    0.78
     propOrder
    0.77
    IUrlHelper
    0.77
     Мексичка
    0.77
     насељу
    0.77
     ErrIntOverflow
    0.73
    ########.
    0.72
    Act Density 0.715%

    No Known Activations