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

    Neuronpedia

    INDEX
    Explanations

    sizing and tuning

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    тися
    0.63
     swab
    0.62
     gruppo
    0.57
     swabs
    0.57
    ienta
    0.56
     instala
    0.56
    grupo
    0.56
     solace
    0.56
    archiviato
    0.55
     tenta
    0.55
    POSITIVE LOGITS
    SizeMode
    0.61
    BySize
    0.60
     சொல்ல
    0.59
    WithPath
    0.57
     wpły
    0.55
     `=`
    0.55
    ший
    0.54
     Calculation
    0.54
    Calculating
    0.54
     曲
    0.54
    Act Density 0.001%

    No Known Activations