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

    Neuronpedia

    INDEX
    Explanations

    shortened present tense verbs

    oai_token-act-pair · gemini-2.0-flash

    varied text excerpts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     taking
    -1.59
     making
    -1.55
     delivering
    -1.55
     producing
    -1.54
     selling
    -1.52
     playing
    -1.52
     sending
    -1.51
     doing
    -1.50
     creating
    -1.49
     forming
    -1.49
    POSITIVE LOGITS
     مرئيه
    0.59
    RefNanny
    0.54
    rungsseite
    0.54
    ьаж
    0.52
    ंदीखरीदारी
    0.52
     EconPapers
    0.47
    Personendaten
    0.47
     surla
    0.46
    addCriterion
    0.43
    مصادر
    0.42
    Act Density 33.166%

    No Known Activations