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

    Neuronpedia

    INDEX
    Explanations

    crime

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aware
    -0.07
    OTION
    -0.07
    239
    -0.06
    हल
    -0.06
    Endpoints
    -0.06
    Comfort
    -0.06
     칼
    -0.06
    Dec
    -0.06
     capabilities
    -0.06
     senators
    -0.06
    POSITIVE LOGITS
    [slot
    0.07
     dobu
    0.07
    rabilir
    0.07
     giy
    0.07
    _FREQUENCY
    0.06
    _notifier
    0.06
     geliştir
    0.06
     timer
    0.06
     donation
    0.06
     sagte
    0.06
    Act Density 0.076%

    No Known Activations