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

    Neuronpedia

    INDEX
    Explanations

    navbar and namespace

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Erm
    0.41
     Anf
    0.40
    \%,
    0.38
    \%)
    0.38
     than
    0.38
    মাংস
    0.38
    住所
    0.37
     Bade
    0.37
    حي
    0.36
    وفي
    0.36
    POSITIVE LOGITS
    brand
    0.67
     navbar
    0.61
    collapse
    0.60
     brand
    0.58
    expand
    0.58
    toggler
    0.58
    品牌
    0.55
    Toggler
    0.55
     expansion
    0.53
     expand
    0.52
    Act Density 0.000%

    No Known Activations