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

    Neuronpedia

    INDEX
    Explanations

    version numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.46
    Absorption
    0.45
    ys
    0.43
    -
    0.42
    Cre
    0.41
    และการ
    0.41
    Talk
    0.40
    EN
    0.40
    Cycl
    0.40
    Diss
    0.40
    POSITIVE LOGITS
    otherArchive
    0.47
    usingCamera
    0.47
     myCamera
    0.46
     kadın
    0.45
    ultimo
    0.45
     dutch
    0.44
     fratello
    0.44
     kuma
    0.44
     moglie
    0.44
    躹
    0.44
    Act Density 0.002%

    No Known Activations