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

    Neuronpedia

    INDEX
    Explanations

    Fiction/dialogue

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     removeFrom
    -0.06
    ‌کنندگان
    -0.06
     Programm
    -0.06
     Stap
    -0.06
    'order
    -0.06
    Subject
    -0.06
    <input
    -0.06
    -dominated
    -0.06
     Mental
    -0.06
    _HP
    -0.06
    POSITIVE LOGITS
     полож
    0.08
    注
    0.07
    _busy
    0.06
    addOn
    0.06
    ega
    0.06
     Pek
    0.06
     shaping
    0.06
     aucun
    0.06
     informed
    0.06
     prowess
    0.06
    Act Density 0.025%

    No Known Activations