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

    Neuronpedia

    INDEX
    Explanations

    assessing conditions and requirements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     učen
    0.41
    urger
    0.40
    দ্দা
    0.40
    હીં
    0.40
    🟣
    0.40
    endi
    0.39
     keseluruhan
    0.39
     mempunyai
    0.39
    intim
    0.38
    arra
    0.38
    POSITIVE LOGITS
    も
    0.42
    Nothing
    0.42
    のス
    0.41
    口
    0.41
    Missing
    0.40
     pièce
    0.40
     WS
    0.39
     Ibid
    0.39
    OR
    0.39
    цеп
    0.39
    Act Density 0.459%

    No Known Activations