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

    Neuronpedia

    INDEX
    Explanations

    when pigs fly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     वर्षी
    0.63
     Enquanto
    0.62
    is
    0.61
     Somewhat
    0.59
    AO
    0.57
    тит
    0.57
    ານ
    0.55
     Understand
    0.55
     своей
    0.55
     godina
    0.55
    POSITIVE LOGITS
    ል
    0.59
     analyzing
    0.59
    lipid
    0.56
     adolescents
    0.55
     ligaments
    0.55
    ه
    0.55
    t
    0.55
     such
    0.55
    가
    0.55
    학
    0.55
    Act Density 0.001%

    No Known Activations