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

    Neuronpedia

    INDEX
    Explanations

    programming or technical instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     như
    0.48
     Ens
    0.48
     elm
    0.47
    ail
    0.46
     собственных
    0.46
    ig
    0.45
    etime
    0.45
     activations
    0.45
     fak
    0.45
     E
    0.44
    POSITIVE LOGITS
    주
    0.52
    jQuery
    0.52
    ז
    0.49
    iteritems
    0.49
    ཌ
    0.48
     শুক্রবার
    0.48
    선을
    0.48
    ྞ
    0.47
     दिसम्बर
    0.47
    海
    0.46
    Act Density 0.000%

    No Known Activations