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

    Neuronpedia

    INDEX
    Explanations

    measurements in metric units

    oai_token-act-pair · gemini-2.0-flash

    non-English or code-related terms

    np_token-act-pair-logits · gpt-4o-mini

    measurements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     poitrine
    -0.50
     légende
    -0.49
     agricole
    -0.47
     intermédiaire
    -0.47
     Einladung
    -0.47
    txtName
    -0.46
     energetically
    -0.46
     princesse
    -0.46
     doublet
    -0.46
     ostavi
    -0.46
    POSITIVE LOGITS
    WriteBarrier
    0.77
    Бахар
    0.75
     فريبيس
    0.73
    تقاوى
    0.66
    Manbalar
    0.66
    脚注の使い方
    0.65
     تضيفلها
    0.63
     snippetHide
    0.60
     kasarigan
    0.60
     CreateTagHelper
    0.60
    Act Density 0.919%

    No Known Activations