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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    それ
    -0.07
    *)_
    -0.07
    (isset
    -0.07
    ToProps
    -0.06
     BlockPos
    -0.06
     loggedIn
    -0.06
     свою
    -0.06
     \<
    -0.06
    واهد
    -0.06
    ')}}"></
    -0.06
    POSITIVE LOGITS
    国内
    0.07
    奧
    0.06
     avoid
    0.06
     archives
    0.06
    EV
    0.06
    eve
    0.06
    _val
    0.06
    環
    0.06
     ря
    0.06
     ghi
    0.06
    Act Density 0.000%

    No Known Activations