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

    Neuronpedia

    INDEX
    Explanations

    references to statistical relationships and numerical values in research data

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

    increase or decline over time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.63
     ujednoznacz
    -0.60
    DataAnnotations
    -0.56
    -0.49
     Exactos
    -0.49
     Arabs
    -0.45
    //};
    -0.45
    >\<^
    -0.44
    UrlResolution
    -0.44
    ьаж
    -0.43
    POSITIVE LOGITS
     menurun
    0.43
     decline
    0.43
     declining
    0.42
     peaked
    0.42
    intellij
    0.41
     peaks
    0.41
     peak
    0.40
    decline
    0.38
     declined
    0.38
    Personensuche
    0.38
    Act Density 0.524%

    No Known Activations