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

    Neuronpedia

    INDEX
    Explanations

    detailed explanations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ۲۶
    -0.07
    ۲۵
    -0.06
    _playing
    -0.06
    .cache
    -0.06
     mất
    -0.06
    長
    -0.06
    PLAN
    -0.06
    nerRadius
    -0.06
    чес
    -0.06
    だよ
    -0.06
    POSITIVE LOGITS
     Deutsche
    0.06
     Soy
    0.06
    UTF
    0.06
    ADOS
    0.06
    enny
    0.06
    Ethernet
    0.06
    袖
    0.06
    一般
    0.06
     شده
    0.06
    /head
    0.05
    Act Density 0.069%

    No Known Activations