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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty or skepticism in relation to personal opinions

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

    about others, most, the, user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -0.48
    ⓧ
    -0.48
    лтамалар
    -0.47
    LEncoder
    -0.46
     виправивши
    -0.43
    IUrlHelper
    -0.42
    Hentet
    -0.42
     ویکی‌پدی
    -0.40
    ⁩
    -0.40
     AttributeSet
    -0.39
    POSITIVE LOGITS
    TagMode
    0.47
     Blech
    0.44
    gridx
    0.43
    Definitely
    0.43
     demais
    0.42
    claimer
    0.42
     Definitely
    0.42
     détaillés
    0.40
    probieren
    0.40
     thua
    0.40
    Act Density 0.004%

    No Known Activations