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

    Neuronpedia

    INDEX
    Explanations

    vice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ma
    -0.07
     ())
    -0.06
    ато
    -0.06
     Maar
    -0.06
     бет
    -0.06
     НА
    -0.06
     verdad
    -0.06
     feminine
    -0.06
     outdated
    -0.06
     runnable
    -0.06
    POSITIVE LOGITS
     vice
    0.08
    _advance
    0.07
     graduate
    0.07
    ulation
    0.07
    .pattern
    0.06
    >'+↵
    0.06
    -factor
    0.06
    _year
    0.06
    HIP
    0.06
     Vice
    0.06
    Act Density 0.001%

    No Known Activations