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

    Neuronpedia

    INDEX
    Explanations

    Rosenblatt noise

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الجهاز
    -0.76
    ımda
    -0.75
     los
    -0.75
    Las
    -0.74
    ления
    -0.73
     Paw
    -0.71
     Moments
    -0.70
    Pastor
    -0.69
     Anf
    -0.69
    niki
    -0.68
    POSITIVE LOGITS
    ۟
    0.81
    mmap
    0.79
    carto
    0.75
    rier
    0.73
    mény
    0.73
    jącej
    0.72
     gehouden
    0.72
     painful
    0.70
    さすがに
    0.70
    dress
    0.70
    Act Density 0.044%

    No Known Activations