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

    Neuronpedia

    INDEX
    Explanations

    instances of personal opinions or strong affirmations

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

    mathematical definitions and questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.83
     nakalista
    -0.75
    AndEndTag
    -0.66
    windowFixed
    -0.66
     فريبيس
    -0.64
     estekak
    -0.63
    rungsseite
    -0.63
    الحياه
    -0.61
    jsxFileName
    -0.61
     chande
    -0.60
    POSITIVE LOGITS
     ambos
    0.33
    igkeiten
    0.32
    simum
    0.32
     beider
    0.31
    atrième
    0.31
    átka
    0.31
    NodeInfo
    0.30
    Ambos
    0.30
     begge
    0.30
     обои
    0.30
    Act Density 0.032%

    No Known Activations