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

    Neuronpedia

    INDEX
    Explanations

    legal compliance and frameworks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    js
    0.47
    O
    0.47
    7
    0.45
     ()
    0.45
    github
    0.44
     OWNER
    0.44
     OÜ
    0.43
     joe
    0.42
    ﺀ
    0.42
     ON
    0.42
    POSITIVE LOGITS
    น
    0.54
    بور
    0.51
    RewardedVideo
    0.49
    punctuation
    0.48
    }}.
    0.48
    muj
    0.47
    راتيج
    0.46
    ن
    0.46
    रेज
    0.46
    箒
    0.46
    Act Density 0.000%

    No Known Activations