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

    Neuronpedia

    INDEX
    Explanations

    Punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     OO
    -0.07
    ISA
    -0.06
     zatím
    -0.06
    koli
    -0.06
    .df
    -0.06
    -Muslim
    -0.06
    issant
    -0.06
     Ukrain
    -0.06
     WR
    -0.06
    ulant
    -0.06
    POSITIVE LOGITS
     Hampton
    0.07
    �
    0.06
    needed
    0.06
    annah
    0.06
    اي
    0.06
     clave
    0.06
    croll
    0.06
    >\
    0.06
     Anth
    0.06
    duğunu
    0.06
    Act Density 0.002%

    No Known Activations