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

    Neuronpedia

    INDEX
    Explanations

    APIs, database, or network carriers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     machte
    0.28
     langer
    0.28
     addirittura
    0.27
     aliran
    0.26
     coton
    0.25
     Alkohol
    0.25
     cittam
    0.25
     sarkar
    0.25
     Magdalena
    0.25
     sogen
    0.25
    POSITIVE LOGITS
    ST
    0.29
    OM
    0.29
    ALL
    0.29
    7
    0.29
    AND
    0.29
    ET
    0.28
    1
    0.28
    ND
    0.28
    OC
    0.28
    6
    0.28
    Act Density 0.255%

    No Known Activations