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

    Neuronpedia

    INDEX
    Explanations

    http and innovation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     steril
    0.48
     frequentemente
    0.46
     pratis
    0.43
    erad
    0.43
     बेरोज
    0.42
     verdiği
    0.42
     receber
    0.41
     bli
    0.41
     berasal
    0.41
    ലുള്ള
    0.41
    POSITIVE LOGITS
    μα
    0.48
    ی
    0.46
    s
    0.44
    ের
    0.43
    senz
    0.43
     Jeu
    0.43
    导
    0.43
    坆
    0.42
    жон
    0.42
    潛
    0.41
    Act Density 0.007%

    No Known Activations