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

    Neuronpedia

    INDEX
    Explanations

    code blocks and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ...',
    0.58
     பெற்று
    0.54
    …
    0.49
    et
    0.49
    lus
    0.48
    overs
    0.48
    …,
    0.47
     se
    0.47
     set
    0.47
     b
    0.46
    POSITIVE LOGITS
    ｝
    1.10
     debugShow
    1.09
    <unused2174>
    1.03
     }
    1.00
     ujarnya
    1.00
     mavenCentral
    0.99
    ❞
    0.98
     Çünkü
    0.95
    atthena
    0.94
    যানী
    0.94
    Act Density 0.385%

    No Known Activations