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

    Neuronpedia

    INDEX
    Explanations

    publicly known through no fault

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝕕
    0.50
    lied
    0.44
     bolts
    0.44
    orescent
    0.43
    separatedBy
    0.43
    carbox
    0.43
    clav
    0.42
     మా
    0.42
     gasket
    0.42
    akka
    0.42
    POSITIVE LOGITS
     Cliente
    0.48
    ногие
    0.46
     Gemeinde
    0.44
    ум
    0.43
    نوع
    0.42
    Report
    0.42
     procurar
    0.42
    Tipo
    0.42
    とにかく
    0.41
     пациентов
    0.41
    Act Density 0.002%

    No Known Activations