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

    Neuronpedia

    INDEX
    Explanations

    programming variables

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ks
    -0.07
    ampus
    -0.06
     puzzles
    -0.06
     verbess
    -0.06
    de
    -0.06
    ð
    -0.06
     удар
    -0.06
     cheaper
    -0.06
     regulators
    -0.06
    rimp
    -0.06
    POSITIVE LOGITS
    كوم
    0.07
     gruesome
    0.06
     medically
    0.06
    BO
    0.06
    言わ
    0.06
     금액
    0.06
     respectable
    0.06
     '../../../../
    0.06
    끼
    0.06
    (grad
    0.06
    Act Density 0.136%

    No Known Activations