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

    Neuronpedia

    INDEX
    Explanations

    Japanese help requests

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ctic
    -0.07
     topLeft
    -0.07
    تقي
    -0.07
    staking
    -0.07
    /sys
    -0.07
    .FAIL
    -0.06
    תקציב
    -0.06
     Indie
    -0.06
    ﻃ
    -0.06
    𝕦
    -0.06
    POSITIVE LOGITS
     remark
    0.08
     Relative
    0.08
     Lou
    0.07
     Adelaide
    0.07
     rinse
    0.07
     initializer
    0.07
     Total
    0.07
    Old
    0.07
    >>>>
    0.07
     LH
    0.07
    Act Density 0.007%

    No Known Activations