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

    Neuronpedia

    INDEX
    Explanations

    the beginning of a document or section that introduces a topic or context

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

    Code, numbers, and symbols

    np_acts-logits-general · gemini-2.0-flash

    discontinuations and fragmentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    akse
    -0.54
    WebVitals
    -0.54
    irmingham
    -0.52
    oida
    -0.51
    rinus
    -0.51
    าก
    -0.51
     Birmingham
    -0.50
     AttributeSet
    -0.50
    uscular
    -0.50
     Gud
    -0.48
    POSITIVE LOGITS
    nesc
    1.02
    tinyos
    0.79
     مرئيه
    0.67
     CreateTagHelper
    0.61
     pellic
    0.58
     houſe
    0.57
    igshid
    0.56
    دانشنامهٔ
    0.56
    parsedMessage
    0.55
    ]),
    0.54
    Act Density 0.030%

    No Known Activations