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

    Neuronpedia

    INDEX
    Explanations

    Manager, Event, Location

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     odour
    0.74
     modestly
    0.72
    ezas
    0.71
     darkened
    0.71
    east
    0.70
    bladder
    0.70
    compressed
    0.66
    dua
    0.66
     riječ
    0.66
    de
    0.65
    POSITIVE LOGITS
     SupCt
    0.82
     okolo
    0.79
    та
    0.76
    BtnUp
    0.73
     SKSpriteNode
    0.73
    branchNode
    0.73
     Mexiko
    0.72
     Bernoulli
    0.72
     افر
    0.72
    رفة
    0.71
    Act Density 0.000%

    No Known Activations