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

    Neuronpedia

    INDEX
    Explanations

    Giving advice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Case
    -0.07
     �
    -0.07
    Crud
    -0.06
    东亚
    -0.06
    赔偿
    -0.06
    ervo
    -0.06
     вопросы
    -0.06
    看完
    -0.06
     civ
    -0.06
    Submitted
    -0.06
    POSITIVE LOGITS
    asticsearch
    0.07
    colour
    0.07
    אחד
    0.07
     dağı
    0.07
     obsł
    0.06
    _return
    0.06
    .floor
    0.06
    🐰
    0.06
    挑选
    0.06
    琎
    0.06
    Act Density 0.132%

    No Known Activations