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

    Neuronpedia

    INDEX
    Explanations

    American

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .register
    -0.08
    째
    -0.08
     dance
    -0.08
    䗪
    -0.07
    	angle
    -0.07
    אפי
    -0.07
    ל
    -0.07
    RefCount
    -0.07
    🅦
    -0.07
    .Cache
    -0.07
    POSITIVE LOGITS
    无视
    0.08
    万人
    0.08
     myths
    0.07
     MW
    0.07
    -setup
    0.07
    Driven
    0.07
    _sets
    0.07
    校区
    0.07
     vibes
    0.07
    .startActivity
    0.07
    Act Density 0.025%

    No Known Activations