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

    Neuronpedia

    INDEX
    Explanations

    Übers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    itecture
    -0.08
    _movie
    -0.08
    (snapshot
    -0.07
     movie
    -0.07
     HDMI
    -0.07
    ilares
    -0.07
     sliders
    -0.07
    leneck
    -0.07
     qe
    -0.07
     Sonic
    -0.07
    POSITIVE LOGITS
    971
    0.08
     crossroads
    0.08
     Fid
    0.08
     Crawford
    0.08
     Mainland
    0.07
     ..
    0.07
     Tuk
    0.07
    ût
    0.07
    mpr
    0.07
    anguage
    0.07
    Act Density 0.000%

    No Known Activations