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

    Neuronpedia

    INDEX
    Explanations

    quantitative data and statistical results related to health or clinical studies

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

    Percentages or numbers with symbols

    np_acts-logits-general · gemini-2.0-flash

    percentages or numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     esternos
    -0.71
     tartalomajánló
    -0.65
     فريبيس
    -0.58
    :✨
    -0.57
     estekak
    -0.57
    RTLD
    -0.54
    ragal
    -0.53
    الدراسه
    -0.52
    səhifə
    -0.51
    出版年
    -0.51
    POSITIVE LOGITS
     compared
    0.50
    Compared
    0.42
    compared
    0.41
     coucher
    0.39
     Compared
    0.37
     ifølge
    0.37
    Despite
    0.33
     katanya
    0.33
     instituição
    0.33
     Haush
    0.32
    Act Density 0.903%

    No Known Activations