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

    Neuronpedia

    INDEX
    Explanations

    and or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    yk
    -0.08
     Pal
    -0.07
    mack
    -0.07
    -0.07
     expression
    -0.07
    ENCY
    -0.06
     rhe
    -0.06
     anti
    -0.06
     stores
    -0.06
     administration
    -0.06
    POSITIVE LOGITS
    òmasyon
    0.08
     wọnyi
    0.08
     wanawake
    0.08
     Quit
    0.08
    Fat
    0.08
     prea
    0.08
     bloody
    0.08
     Orioles
    0.08
     Fat
    0.08
    డ్డ
    0.08
    Act Density 0.123%
    No Known Activations