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

    Neuronpedia

    INDEX
    Explanations

    IM

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Scientists
    -0.07
    PasswordField
    -0.07
     retired
    -0.07
    attered
    -0.06
     forensic
    -0.06
     fucked
    -0.06
    Fuel
    -0.06
     contacted
    -0.06
     Limits
    -0.06
    ávě
    -0.06
    POSITIVE LOGITS
    extAlignment
    0.07
     utilizando
    0.07
     strpos
    0.06
     Synd
    0.06
    orraine
    0.06
    osyal
    0.06
    жение
    0.06
     anarchists
    0.06
     aşağı
    0.06
    iš
    0.06
    Act Density 0.000%

    No Known Activations