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

    Neuronpedia

    INDEX
    Explanations

    chemistry

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    劣势
    -0.07
     exemplary
    -0.07
     ayrı
    -0.07
     bóng
    -0.07
    plemented
    -0.07
     undertaking
    -0.07
     Disorder
    -0.07
    ア
    -0.07
    logging
    -0.07
    𝕷
    -0.07
    POSITIVE LOGITS
    coupon
    0.08
     ------------------------------------------------
    0.07
     ropes
    0.07
     craft
    0.07
    你想
    0.07
     Carl
    0.07
    loop
    0.07
    uzu
    0.07
    _CE
    0.07
     ان
    0.07
    Act Density 0.008%

    No Known Activations