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

    Neuronpedia

    INDEX
    Explanations

    Technical documents / Q&A

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     paul
    -0.07
    _paint
    -0.07
    ו�
    -0.06
    etary
    -0.06
     Stap
    -0.06
     Chaos
    -0.06
    Ultra
    -0.06
    Labour
    -0.06
    ependency
    -0.06
     ejected
    -0.06
    POSITIVE LOGITS
    Collector
    0.06
     mệnh
    0.06
     correctamente
    0.06
     ():
    0.06
    思い
    0.06
    〇
    0.06
    Folder
    0.06
    必要
    0.06
     روی
    0.06
     حم
    0.06
    Act Density 0.000%

    No Known Activations