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

    Neuronpedia

    INDEX
    Explanations

    <

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Salt
    -0.06
     crime
    -0.06
     segunda
    -0.06
    _ANS
    -0.06
     frog
    -0.06
     Lever
    -0.06
    腹
    -0.06
     nik
    -0.06
    ODY
    -0.06
    ělí
    -0.06
    POSITIVE LOGITS
     TE
    0.07
    >').
    0.07
     finanzi
    0.07
     expects
    0.07
    _named
    0.06
    없음
    0.06
     až
    0.06
     Regel
    0.06
    _mc
    0.06
     потом
    0.06
    Act Density 0.003%

    No Known Activations