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

    Neuronpedia

    INDEX
    Explanations

    special characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ม
    0.53
    ي
    0.52
    Ռ
    0.51
     showered
    0.47
    이스
    0.46
    Бе
    0.44
    യില
    0.44
    𝓑
    0.44
    ंस
    0.44
    يتر
    0.43
    POSITIVE LOGITS
     écr
    0.42
     emerge
    0.41
     gall
    0.41
     cycles
    0.41
    flies
    0.41
     instrumentos
    0.41
     at
    0.41
     CHO
    0.40
     hinaus
    0.40
     filhos
    0.40
    Act Density 0.000%

    No Known Activations