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

    Neuronpedia

    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lond
    -0.07
    робіт
    -0.07
    を見る
    -0.06
     आई
    -0.06
    "strconv
    -0.06
     τι
    -0.06
     gắng
    -0.06
    Tonight
    -0.06
    /disc
    -0.06
    (ConfigurationManager
    -0.06
    POSITIVE LOGITS
    heiten
    0.06
     Dirk
    0.06
     padre
    0.06
     />\
    0.06
    CHEMY
    0.06
     illusions
    0.05
    	K
    0.05
    Amy
    0.05
     Alpha
    0.05
     MVP
    0.05
    Act Density 0.073%

    No Known Activations