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

    Neuronpedia

    INDEX
    Explanations

    numerical data and variables in a mathematical or statistical context

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

    mathematical sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الرياضيه
    -0.41
     كومونز
    -0.40
     للاسماء
    -0.39
     surla
    -0.37
    #+#
    -0.37
     חיצוניים
    -0.37
     للمعارف
    -0.37
    μβρίου
    -0.36
     Numerade
    -0.36
     typelib
    -0.35
    POSITIVE LOGITS
    Personendaten
    0.58
     poffe
    0.54
    PerformLayout
    0.53
     myſelf
    0.53
     raiſ
    0.52
     Anſ
    0.48
     poffible
    0.47
     fometimes
    0.47
    windowFixed
    0.47
    titleMargin
    0.47
    Act Density 0.308%

    No Known Activations