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

    Neuronpedia

    INDEX
    Explanations

    cross-origin resource sharing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pH
    0.46
     beverages
    0.44
     Crawford
    0.43
     beverage
    0.42
    缆
    0.41
     Franch
    0.41
     vlo
    0.41
     hydroly
    0.40
     Gaff
    0.40
     wines
    0.40
    POSITIVE LOGITS
    hund
    0.47
    полу
    0.47
    pist
    0.44
    म
    0.44
    Alberto
    0.44
     அலெ
    0.44
     Elemente
    0.44
    pj
    0.43
     पवार
    0.43
    Immediate
    0.43
    Act Density 0.000%

    No Known Activations