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

    Neuronpedia

    INDEX
    Explanations

    spectrum

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    學院
    -0.07
    chang
    -0.06
     Damian
    -0.06
     cas
    -0.06
     pedals
    -0.06
    ampton
    -0.06
     Parties
    -0.06
     Lon
    -0.06
     рассказ
    -0.06
    /fonts
    -0.06
    POSITIVE LOGITS
    率
    0.07
     thấy
    0.07
     симптом
    0.07
    减
    0.06
     پیک
    0.06
    pageNumber
    0.06
     conserve
    0.06
    .spec
    0.06
     использовать
    0.06
    他们
    0.06
    Act Density 0.002%

    No Known Activations