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

    Neuronpedia

    INDEX
    Explanations

    body parts and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    VRDR
    0.75
    ObjectUnderTest
    0.74
    Hãy
    0.65
     cdot
    0.64
    izoen
    0.63
    gramModel
    0.61
    Excerpt
    0.61
    PropertyParam
    0.61
     يحتوي
    0.61
     zowel
    0.61
    POSITIVE LOGITS
     over
    0.85
     from
    0.83
     to
    0.79
     up
    0.74
     find
    0.73
     finding
    0.73
     with
    0.73
     on
    0.73
     upon
    0.73
     normally
    0.72
    Act Density 0.001%

    No Known Activations