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

    Neuronpedia

    INDEX
    Explanations

    Med

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    λογ
    -0.07
    १
    -0.06
     FUCK
    -0.06
    IDADE
    -0.06
     زیب
    -0.06
     linh
    -0.06
    歳
    -0.06
     شیر
    -0.06
     Fé
    -0.06
    BOOK
    -0.06
    POSITIVE LOGITS
    .dispose
    0.07
    ريك
    0.07
    Fmt
    0.07
    drs
    0.07
    ýš
    0.07
    .air
    0.06
    length
    0.06
    :result
    0.06
     demo
    0.06
    expand
    0.06
    Act Density 0.146%

    No Known Activations