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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     skin
    -0.07
     bakery
    -0.07
     fists
    -0.06
    �
    -0.06
    手
    -0.06
     pledge
    -0.06
    Downloads
    -0.06
     Nar
    -0.06
    类
    -0.06
     ownership
    -0.06
    POSITIVE LOGITS
     çocu
    0.07
    _vi
    0.07
    ån
    0.07
     самых
    0.06
    INT
    0.06
     J
    0.06
    "is
    0.06
    ταν
    0.06
     keras
    0.06
    _restart
    0.06
    Act Density 0.000%

    No Known Activations