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

    Neuronpedia

    INDEX
    Explanations

    Word count/programming functions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     пособ
    -0.08
    рения
    -0.08
    форма
    -0.08
     подраздел
    -0.08
     настав
    -0.08
    нив
    -0.08
     фанта
    -0.08
     драй
    -0.08
    פורט
    -0.08
    итив
    -0.08
    POSITIVE LOGITS
    /count
    0.10
     counts
    0.10
    =len
    0.09
     contando
    0.09
    .count
    0.09
     counting
    0.09
     contador
    0.09
     computes
    0.08
     Counts
    0.08
    -count
    0.08
    Act Density 0.002%

    No Known Activations