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

    Neuronpedia

    INDEX
    Explanations

    restrict

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tit
    -0.08
     Jungle
    -0.07
     Immun
    -0.07
     Phen
    -0.07
     GHz
    -0.07
    .$.
    -0.07
    Cancellation
    -0.07
    frontend
    -0.07
    nice
    -0.07
    免疫
    -0.06
    POSITIVE LOGITS
    альных
    0.08
    꿧
    0.08
    منظم
    0.07
     "'.$
    0.07
    小龙
    0.07
     establishing
    0.07
    注意
    0.07
     analsex
    0.07
    떳
    0.07
     strncpy
    0.07
    Act Density 0.001%

    No Known Activations