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

    Neuronpedia

    INDEX
    Explanations

    terms related to user data and privacy policies

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

    Follows "our," "a," or "to"

    np_acts-logits-general · gemini-2.0-flash

    Our basis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PMailer
    -0.69
    UnknownFieldSet
    -0.66
     Réponses
    -0.65
    GMENT
    -0.64
    AndEndTag
    -0.60
    jsonwebtoken
    -0.57
    esterday
    -0.57
     محفوظة
    -0.56
    raborty
    -0.55
     endwhile
    -0.54
    POSITIVE LOGITS
    awtextra
    0.53
     huy
    0.48
     Pira
    0.47
    čet
    0.45
     Andra
    0.45
    aimerais
    0.44
    FAIL
    0.44
    ytick
    0.44
    Basis
    0.43
    ględ
    0.43
    Act Density 0.009%

    No Known Activations