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

    Neuronpedia

    INDEX
    Explanations

    go fmt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ו
    1.50
    м
    1.40
    atau
    1.22
    ी
    1.20
    ity
    1.17
    essay
    1.13
    ి
    1.12
    me
    1.11
    ي
    1.10
    nya
    1.08
    POSITIVE LOGITS
    aviti
    1.30
    бліоте
    1.25
    рит
    1.23
     seamen
    1.23
     prototyping
    1.22
     fuselage
    1.20
    ʳ
    1.17
    Autoresizing
    1.17
     manpower
    1.16
     vase
    1.15
    Act Density 0.149%

    No Known Activations