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

    Neuronpedia

    INDEX
    Explanations

    segments related to data structures and programming syntax

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

    subject headings and variable names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    inSlope
    -0.40
     flota
    -0.39
     Δια
    -0.37
     kece
    -0.36
    Diwedd
    -0.36
     Picchu
    -0.36
    Soorten
    -0.34
     Wellen
    -0.34
     darse
    -0.34
     ungef
    -0.34
    POSITIVE LOGITS
     subject
    1.50
    subject
    1.43
     Subject
    1.40
     subjects
    1.38
    Subject
    1.32
     Subjects
    1.28
    Subjects
    1.27
    getSubject
    1.26
    subjects
    1.23
    SUBJECT
    1.22
    Act Density 0.021%

    No Known Activations