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

    Neuronpedia

    INDEX
    Explanations

    explains to target or willingness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     정상
    0.47
     계산
    0.43
     образовањем
    0.43
     टीम
    0.41
    ∗</
    0.40
    !।
    0.40
    offsetTop
    0.40
     nisid
    0.40
    playerPosition
    0.40
     ಕರ್
    0.39
    POSITIVE LOGITS
     récemment
    0.47
     Cortana
    0.47
     bagno
    0.45
    erde
    0.43
     bandes
    0.43
     één
    0.42
     Cru
    0.40
     décision
    0.40
     verdad
    0.40
     radicals
    0.40
    Act Density 0.004%

    No Known Activations