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

    Neuronpedia

    INDEX
    Explanations

    terms related to difficulty and ease of learning or tasks

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

    effort and difficulty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RTLR
    -0.45
     محفوظة
    -0.42
    srcs
    -0.42
    Narrative
    -0.42
     satirical
    -0.41
     narrative
    -0.41
    Zone
    -0.40
    TProtocol
    -0.40
     Narrative
    -0.39
     Zone
    -0.39
    POSITIVE LOGITS
     Taktlose
    0.61
    ⓧ
    0.55
     surla
    0.55
    tagHelperRunner
    0.54
    EndProject
    0.53
     kapture
    0.44
    ंदीखरीदारी
    0.44
     esternos
    0.44
     continúas
    0.42
     męska
    0.41
    Act Density 0.165%

    No Known Activations