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

    Neuronpedia

    INDEX
    Explanations

    imperative phrases or directions that prompt the reader to observe or consider something

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

    look at this

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     naselje
    -0.32
    Зву
    -0.30
    jstor
    -0.30
     Annahme
    -0.29
     חיצוניים
    -0.28
     ſeveral
    -0.28
    FromString
    -0.27
    iestety
    -0.27
     hopes
    -0.27
     schuldig
    -0.27
    POSITIVE LOGITS
    LookAnd
    0.73
     ujednoznacz
    0.67
     المعيارى
    0.65
    expandindo
    0.59
    webElementXpaths
    0.52
     AssemblyTitle
    0.52
    \{\\
    0.52
    dexter
    0.51
    afficheront
    0.51
    thâu
    0.51
    Act Density 0.015%

    No Known Activations