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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iná
    -0.07
    Inner
    -0.07
     Slut
    -0.06
     dragon
    -0.06
    parallel
    -0.06
    Moon
    -0.06
     tailor
    -0.06
     prom
    -0.06
    لام
    -0.06
    rarian
    -0.06
    POSITIVE LOGITS
    .getSharedPreferences
    0.07
    -under
    0.07
    /il
    0.07
     maxi
    0.07
    .setOnAction
    0.07
     счит
    0.06
     вза
    0.06
    资
    0.06
    'y
    0.06
    _WEAPON
    0.06
    Act Density 0.223%

    No Known Activations