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

    Neuronpedia

    INDEX
    Explanations

    Awe

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    基本上都
    -0.07
    캴
    -0.07
     realistically
    -0.07
    确立
    -0.07
     unpopular
    -0.07
     достижени
    -0.07
     Karl
    -0.07
    這一
    -0.07
    סחר
    -0.07
    -container
    -0.06
    POSITIVE LOGITS
     היש
    0.07
    ↟
    0.07
    승
    0.07
    opa
    0.07
    宾
    0.07
    ட
    0.07
     zo
    0.07
    -lib
    0.07
    iona
    0.07
    _route
    0.07
    Act Density 0.043%

    No Known Activations