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

    Neuronpedia

    INDEX
    Explanations

    statistical terminology and significant results in data analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    how something happens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Infórmanos
    -0.58
     ujednoznacz
    -0.54
     Taktlose
    -0.54
    SharedCtor
    -0.54
     CreateTagHelper
    -0.52
    afficheront
    -0.50
    évaluateur
    -0.48
     ویکی‌پدی
    -0.47
    Nationalité
    -0.46
    rizona
    -0.46
    POSITIVE LOGITS
    <eos>
    0.49
     שוליים
    0.41
    الدراسه
    0.40
     pops
    0.39
    dew
    0.39
    Hentet
    0.39
    amsa
    0.38
    arme
    0.38
    etz
    0.38
     Consumers
    0.38
    Act Density 3.705%

    No Known Activations