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

    Neuronpedia

    INDEX
    Explanations

    utf-8 file encoding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Summary
    0.41
     faire
    0.39
     Chart
    0.39
     Semi
    0.38
     Dice
    0.38
     Fill
    0.38
     typography
    0.38
    敖
    0.38
     ખાસ
    0.37
     Faire
    0.37
    POSITIVE LOGITS
    zik
    0.41
     cp
    0.38
     ziff
    0.38
    修理
    0.37
    呵
    0.37
    upu
    0.36
    unicode
    0.36
    झाने
    0.36
     overruling
    0.36
     greek
    0.35
    Act Density 0.003%

    No Known Activations