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

    Neuronpedia

    INDEX
    Explanations

    parser =

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Cite
    1.47
    عات
    1.38
     ouvir
    1.32
     tekr
    1.28
    handlers
    1.27
     conter
    1.26
     что
    1.24
     তুলনা
    1.24
     seperti
    1.24
    texttt
    1.23
    POSITIVE LOGITS
    ോ
    1.36
     phenytoin
    1.36
    🏻
    1.32
    itics
    1.30
    1.28
    🏾
    1.27
    🏽
    1.25
    ühl
    1.24
    1.24
    ︎
    1.23
    Act Density 0.002%

    No Known Activations