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

    Neuronpedia

    INDEX
    Explanations

    nCr, n, cells, formulas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TRAN
    0.55
    Bone
    0.47
    囯
    0.46
    Doc
    0.46
    Diffuse
    0.46
    Datas
    0.45
    Outputs
    0.45
    Input
    0.45
    பதி
    0.45
    Spray
    0.43
    POSITIVE LOGITS
     ineligible
    0.54
     recent
    0.49
     их
    0.48
     their
    0.47
    లు
    0.47
     मुश्किल
    0.46
     petty
    0.45
     collapsed
    0.45
     pasado
    0.45
    었다
    0.45
    Act Density 0.003%

    No Known Activations