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

    Neuronpedia

    INDEX
    Explanations

    common words after punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Drupal
    0.38
     Python
    0.37
    OptionsMenu
    0.37
     С
    0.36
    ี่
    0.36
     пере
    0.36
     API
    0.36
     SU
    0.36
     {\
    0.35
     versi
    0.35
    POSITIVE LOGITS
    been
    0.45
    would
    0.41
     thoſe
    0.41
    their
    0.40
    have
    0.39
     untenable
    0.37
     للغاية
    0.37
     been
    0.36
    know
    0.36
    small
    0.36
    Act Density 0.023%

    No Known Activations