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

    Neuronpedia

    INDEX
    Explanations

    hidden disturbing messages signals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ಪಡ
    0.39
     захо
    0.38
    迪士尼
    0.38
    轰
    0.38
     vale
    0.37
     ווא
    0.37
    測試
    0.37
    盒
    0.37
    ឮ
    0.37
    ហ៊
    0.36
    POSITIVE LOGITS
     Adjustment
    0.38
    larım
    0.38
    Adjustment
    0.38
     बुद्धि
    0.38
     Smartphone
    0.37
    CameraOpened
    0.37
     Adası
    0.37
     Corfu
    0.36
     Smartphones
    0.36
    ESCO
    0.36
    Act Density 0.000%

    No Known Activations