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

    Neuronpedia

    INDEX
    Explanations

    mismatch

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    élé
    -0.08
     ústav
    -0.08
    伝
    -0.07
    orary
    -0.07
    ельзя
    -0.07
    orgia
    -0.07
    cích
    -0.07
     Praze
    -0.06
     franca
    -0.06
    (coordinates
    -0.06
    POSITIVE LOGITS
     mismatch
    0.08
    ismatch
    0.07
    ism
    0.07
    ()%
    0.07
    ISM
    0.06
     تجه
    0.06
     workouts
    0.06
     mism
    0.06
     match
    0.06
     disruption
    0.06
    Act Density 0.002%

    No Known Activations