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

    Neuronpedia

    INDEX
    Explanations

    Jr

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lam
    -0.07
     cade
    -0.06
    ่ม
    -0.06
     putting
    -0.06
     станов
    -0.06
    InView
    -0.06
    #ifdef
    -0.06
     secure
    -0.06
     SER
    -0.06
     Sche
    -0.06
    POSITIVE LOGITS
    ieties
    0.09
    ervers
    0.07
    אורח
    0.07
     arousal
    0.07
    髎
    0.07
     süreç
    0.07
    就连
    0.07
    askell
    0.07
     modulation
    0.07
     سي
    0.07
    Act Density 0.003%

    No Known Activations