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

    Neuronpedia

    INDEX
    Explanations

    specific punctuation marks and symbols used in programming or markup languages

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

    section and figure labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.54
     surla
    -0.53
    AndEndTag
    -0.51
     SqlConnection
    -0.48
    aarrggbb
    -0.47
    VYMaps
    -0.46
    ThroughAttribute
    -0.45
    Kjelder
    -0.44
    styleType
    -0.43
    chränk
    -0.41
    POSITIVE LOGITS
    endregion
    0.45
    toBeTruthy
    0.45
    omenclature
    0.43
    omencl
    0.43
    culum
    0.42
     _('
    0.40
     _("
    0.40
    fficiency
    0.40
     names
    0.40
    (__('
    0.39
    Act Density 0.002%

    No Known Activations