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

    Neuronpedia

    INDEX
    Explanations

    annotation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     वेरिए
    0.46
    壹百
    0.46
     grossesse
    0.45
     htob
    0.44
    鰻
    0.44
    <unused27>
    0.44
     rmse
    0.43
    ianSpace
    0.43
     lèvres
    0.42
     पत्थर
    0.42
    POSITIVE LOGITS
    annotation
    1.18
     annotation
    0.89
    Annotation
    0.85
     Annotation
    0.84
    annot
    0.77
     annotations
    0.76
     annot
    0.66
    annotate
    0.66
    注解
    0.65
     annotated
    0.64
    Act Density 0.001%

    No Known Activations