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

    Neuronpedia

    INDEX
    Explanations

    numerical values and references to time periods or events

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

    Years or numbers followed by punctuation

    np_acts-logits-general · gemini-2.0-flash

    years and dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Hentet
    -0.44
     galinha
    -0.39
     själva
    -0.39
     peine
    -0.38
     defaultstate
    -0.36
    bibnamefont
    -0.35
     wspar
    -0.34
    ñora
    -0.34
    éndolo
    -0.33
     mitään
    -0.33
    POSITIVE LOGITS
     للمعارف
    0.73
    FunctionFlags
    0.56
    MessageOf
    0.56
    postIndex
    0.54
    ôtel
    0.54
    VersionUID
    0.52
    MessageState
    0.52
    WithIOException
    0.51
    AsUp
    0.51
    figsize
    0.51
    Act Density 0.632%

    No Known Activations