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

    Neuronpedia

    INDEX
    Explanations

    grammar check

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused2147>
    0.72
    <unused2109>
    0.69
    <unused2137>
    0.68
    <unused2134>
    0.65
    <unused2170>
    0.65
    <unused2118>
    0.62
    <unused2141>
    0.62
    }_{+}^{
    0.61
    પરા
    0.61
    <unused2185>
    0.60
    POSITIVE LOGITS
    G
    2.10
     G
    1.90
    GC
    1.86
    Gs
    1.86
    GP
    1.81
    GR
    1.76
     GP
    1.76
    Г
    1.74
    GA
    1.72
    GB
    1.71
    Act Density 1.603%

    No Known Activations