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

    Neuronpedia

    INDEX
    Explanations

    line

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    еÑģÑĤво
    -0.31
     account
    -0.31
     PLAN
    -0.28
    db
    -0.26
    æ±¾
    -0.26
    uran
    -0.26
    Sem
    -0.26
    oo
    -0.25
    erg
    -0.25
    sem
    -0.25
    POSITIVE LOGITS
    æĿijæ°ij
    0.29
    å±Ĥ次
    0.28
    纪å§Ķ书记
    0.27
    laus
    0.26
    æĬĬæīĭ
    0.26
    lexport
    0.26
    uments
    0.25
    aser
    0.25
    å®Įæķ´æĢ§
    0.25
    icot
    0.24
    Act Density 0.905%

    No Known Activations