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

    Neuronpedia

    INDEX
    Explanations

    Google DeepMind

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     $%
    0.42
    Ethoxy
    0.42
    mathscr
    0.41
     সৌর
    0.41
    🖤
    0.40
     gypsy
    0.39
     fru
    0.39
     букмекердик
    0.38
     quyển
    0.38
     연료
    0.38
    POSITIVE LOGITS
     Google
    0.80
    Google
    0.74
     Goog
    0.73
    google
    0.67
     google
    0.66
     goog
    0.62
    GOOGLE
    0.59
    goog
    0.54
    谷歌
    0.53
     Gmail
    0.50
    Act Density 0.180%

    No Known Activations