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

    Neuronpedia

    INDEX
    Explanations

    dont know or dont require

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Н
    2.83
    Ф
    2.46
    Η
    2.31
    К
    2.26
    Л
    2.17
    ✓
    2.15
    𝗡
    2.10
    Algun
    2.09
    CH
    2.08
    Μ
    2.07
    POSITIVE LOGITS
    ऩे
    2.37
    ು
    2.26
    δήποτε
    2.17
    ן
    1.95
    ae
    1.94
    cja
    1.90
     shout
    1.86
    mselves
    1.85
    oretical
    1.80
    gia
    1.79
    Act Density 0.261%

    No Known Activations