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

    Neuronpedia

    INDEX
    Explanations

    explains content following a reference

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tx
    0.49
    発生
    0.49
     लोकसभा
    0.48
    鐗
    0.48
     Parmesan
    0.46
    詛
    0.46
     choroby
    0.44
    ǒ
    0.44
    暗示
    0.44
    豆
    0.43
    POSITIVE LOGITS
     bila
    0.44
     eclectic
    0.42
     icons
    0.40
     zus
    0.39
     seni
    0.39
     tuned
    0.38
     avant
    0.38
     dotycz
    0.38
     invers
    0.38
     immersion
    0.38
    Act Density 0.005%

    No Known Activations