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

    Neuronpedia

    INDEX
    Explanations

    integer type in programming

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ]
    1.13
    )
    1.09
    }
    1.00
    i
    0.91
    ಿ
    0.88
    δος
    0.86
     artículos
    0.85
     (
    0.82
    harth
    0.82
    ിയി
    0.81
    POSITIVE LOGITS
    お
    0.89
    ش
    0.88
    د
    0.87
    ty
    0.85
    int
    0.80
    ш
    0.79
    2
    0.77
    赓
    0.73
    ED
    0.72
    る
    0.72
    Act Density 0.042%

    No Known Activations