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

    Neuronpedia

    INDEX
    Explanations

    portal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ing
    3.30
    ੀ
    3.21
    ीकरण
    3.21
    ेक्ट
    3.18
    tel
    3.18
    tion
    3.16
    я
    3.04
    er
    2.85
    кта
    2.83
    هما
    2.75
    POSITIVE LOGITS
    に
    3.40
    ن
    3.37
    ש
    3.36
    ような
    3.21
    また
    3.11
    課程
    2.96
    ів
    2.96
    ב
    2.95
    स
    2.91
    রাজের
    2.89
    Act Density 0.015%

    No Known Activations