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
     ενώ
    -0.07
    %),
    -0.06
     سپتامبر
    -0.06
    andReturn
    -0.06
    &display
    -0.06
    StatusBar
    -0.06
    trust
    -0.06
     hud
    -0.06
     photographers
    -0.06
     twitter
    -0.06
    POSITIVE LOGITS
     cardio
    0.07
    گی
    0.06
     edeb
    0.06
    スレ
    0.06
    ีม
    0.06
     �
    0.06
    -parameter
    0.06
     Ging
    0.06
    _beh
    0.06
    领
    0.06
    Act Density 0.002%

    No Known Activations