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

    Neuronpedia

    INDEX
    Explanations

    ="

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     orgy
    -0.07
    rms
    -0.06
    arest
    -0.06
     gỗ
    -0.06
    avad
    -0.06
     nemoc
    -0.06
     Geneva
    -0.06
    TEGR
    -0.06
     NK
    -0.06
    ब
    -0.06
    POSITIVE LOGITS
    plex
    0.07
     Περι
    0.07
    应
    0.06
    =this
    0.06
    链接
    0.06
     LDL
    0.06
     bỏ
    0.06
     yürüt
    0.06
     selber
    0.06
    .quick
    0.06
    Act Density 0.016%

    No Known Activations