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

    Neuronpedia

    INDEX
    Explanations

    references to statistical data and results

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

    percentages and differences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الرياضيه
    -0.65
    -0.63
    تقاوى
    -0.62
     betweenstory
    -0.58
    Portály
    -0.54
    SPJ
    -0.54
     Audiodateien
    -0.52
     ""))
    -0.52
     zoude
    -0.51
    CRD
    -0.51
    POSITIVE LOGITS
     årets
    0.41
     consultato
    0.34
     surla
    0.34
     состоя
    0.33
     improved
    0.33
    improved
    0.32
    orated
    0.32
     increased
    0.31
    enterOuterAlt
    0.31
     Vordergrund
    0.31
    Act Density 0.097%

    No Known Activations