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

    Neuronpedia

    INDEX
    Explanations

    chess notation moves

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    clinton
    0.25
     kanamycin
    0.22
     کرتی
    0.21
    sqlUpdate
    0.21
    쨌
    0.21
     کرتا
    0.21
     dechlorination
    0.21
    Skippable
    0.20
    愪
    0.20
     সত্যাগ্রহ
    0.20
    POSITIVE LOGITS
    ,
    0.25
     pre
    0.23
    pre
    0.22
     f
    0.22
    =
    0.21
    /
    0.21
     in
    0.21
     H
    0.20
    -
    0.20
    $
    0.19
    Act Density 0.001%

    No Known Activations