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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tinder
    -0.07
    Occurrences
    -0.07
    ➯
    -0.07
    ]];↵
    -0.07
    Moder
    -0.07
    ديث
    -0.07
     implants
    -0.07
    �
    -0.07
    �
    -0.06
    一瞬间
    -0.06
    POSITIVE LOGITS
    .il
    0.07
    佽
    0.07
    pósito
    0.06
    .training
    0.06
    Ƴ
    0.06
    扬州
    0.06
    aki
    0.06
     Daly
    0.06
    bad
    0.06
    _dw
    0.06
    Act Density 0.003%

    No Known Activations