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

    Neuronpedia

    INDEX
    Explanations

    ESLint, logger, auth, new bonds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    不再
    0.41
    सेना
    0.40
    કમાં
    0.39
    อย่าง
    0.38
     Ж
    0.38
    heden
    0.37
    弋
    0.37
    xFFFF
    0.36
    ısından
    0.36
    urrence
    0.36
    POSITIVE LOGITS
     humaines
    0.46
     humains
    0.45
     вироб
    0.45
    VELOP
    0.44
     icch
    0.43
     semplici
    0.41
    ク
    0.41
     製品
    0.41
     inimes
    0.41
    ин
    0.40
    Act Density 0.001%

    No Known Activations