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

    Neuronpedia

    INDEX
    Explanations

    informal phrases with got or want

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    p
    0.55
    pady
    0.52
    m
    0.50
    t
    0.49
    cione
    0.45
    {
    0.45
    USTOM
    0.44
    EL
    0.43
    KNN
    0.43
    Green
    0.42
    POSITIVE LOGITS
     nerdy
    0.50
     summation
    0.48
     মুক্তিযোদ্ধ
    0.45
    გან
    0.45
     probiotics
    0.45
     séptimo
    0.44
    的
    0.44
    의
    0.43
     dabb
    0.43
    াই
    0.43
    Act Density 0.000%

    No Known Activations