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

    Neuronpedia

    INDEX
    Explanations

    Grading rubrics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Cop
    -0.08
     predstavlja
    -0.08
    uil
    -0.08
     sweetest
    -0.08
    ialize
    -0.07
     dulce
    -0.07
     ufficial
    -0.07
    Verified
    -0.07
    베
    -0.07
     correctly
    -0.07
    POSITIVE LOGITS
     hingegen
    0.11
     nich
    0.09
    拒
    0.09
    失败
    0.09
     NG
    0.09
     onvoldoende
    0.09
     squander
    0.09
     haste
    0.09
     struggling
    0.09
    unne
    0.08
    Act Density 0.076%

    No Known Activations