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

    Neuronpedia

    INDEX
    Explanations

    people

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ynet
    -0.07
     increment
    -0.07
     груз
    -0.07
     Stitch
    -0.06
     khi
    -0.06
     innov
    -0.06
    .artist
    -0.06
     overl
    -0.06
     Weak
    -0.06
    摄
    -0.06
    POSITIVE LOGITS
    \",\
    0.07
     Facts
    0.07
    شمالی
    0.07
    两人
    0.06
     pornô
    0.06
    Slash
    0.06
    Experts
    0.06
    erg
    0.06
    SEP
    0.06
    еко
    0.06
    Act Density 0.022%

    No Known Activations