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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     лег
    -0.07
    (Channel
    -0.07
    анный
    -0.07
     irrespective
    -0.07
    _IDS
    -0.07
    .Can
    -0.07
    픽
    -0.06
     które
    -0.06
    izer
    -0.06
    egrity
    -0.06
    POSITIVE LOGITS
     ninete
    0.08
    Images
    0.07
    Admin
    0.06
    *w
    0.06
     Flake
    0.06
    [axis
    0.06
     prostitu
    0.06
    -football
    0.06
     Lal
    0.06
    Powered
    0.06
    Act Density 0.005%

    No Known Activations