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

    Neuronpedia

    INDEX
    Explanations

    Quotation punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Mutex
    -0.07
    consulta
    -0.06
     Türkçe
    -0.06
     Hollywood
    -0.06
    eso
    -0.06
    цит
    -0.06
     Puerto
    -0.06
    interp
    -0.06
    MAR
    -0.06
    λευ
    -0.06
    POSITIVE LOGITS
    ">↵
    0.06
     exc
    0.06
     창
    0.06
     bg
    0.06
     �
    0.06
    Choices
    0.06
    无码
    0.06
    ↵
↵
    0.06
    َف
    0.06
    ै
    0.06
    Act Density 0.017%

    No Known Activations