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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty or questioning

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

    followed by "that," "in," or "to"

    np_acts-logits-general · gemini-2.0-flash

    abstract states and circumstances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    خابات
    -0.57
    YGON
    -0.57
    mals
    -0.55
    )}
    -0.55
     Malam
    -0.53
    gyz
    -0.53
    }{*}{
    -0.53
     _('
    -0.53
    ("}");
    -0.52
     ivelany
    -0.52
    POSITIVE LOGITS
     تضيفلها
    0.81
    tagHelperRunner
    0.78
    WireFormatLite
    0.73
    UnusedPrivate
    0.71
    مراجع
    0.71
    Diweddarwch
    0.68
    WriteTagHelper
    0.64
    曖昧さ回避
    0.64
     متعلقه
    0.64
     whatsoever
    0.64
    Act Density 0.545%

    No Known Activations