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

    Neuronpedia

    INDEX
    Explanations

    understand early stages and key areas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hues
    0.52
     fatto
    0.50
     redirects
    0.47
    egger
    0.45
     tule
    0.45
     cultivars
    0.45
     newbies
    0.45
    t
    0.45
     outings
    0.44
     materiaal
    0.43
    POSITIVE LOGITS
    0
    0.50
    2
    0.48
    Spectrum
    0.46
    フレーム
    0.45
    Illuminate
    0.44
    Curve
    0.44
    infix
    0.44
     ஆலோச
    0.43
    FunctionName
    0.43
    ially
    0.43
    Act Density 0.001%

    No Known Activations