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

    Neuronpedia

    INDEX
    Explanations

    special action terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝙀
    0.49
    као
    0.48
    igneur
    0.48
    depending
    0.48
    кен
    0.47
    ütfen
    0.46
    餞
    0.46
    وامی
    0.45
    зне
    0.45
    던
    0.45
    POSITIVE LOGITS
     Diagn
    0.48
     Tisch
    0.45
     ODE
    0.45
     Narr
    0.45
     Cafe
    0.43
     Bets
    0.43
     therapist
    0.43
     humanities
    0.42
     R
    0.42
     café
    0.42
    Act Density 0.001%

    No Known Activations