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

    Neuronpedia

    INDEX
    Explanations

    legal citations or code artifacts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rā
    -0.81
    mannen
    -0.81
     skak
    -0.80
     COMPARISON
    -0.79
    gods
    -0.79
    rijving
    -0.77
     baixar
    -0.77
     aben
    -0.76
     richard
    -0.76
     limão
    -0.75
    POSITIVE LOGITS
     another
    0.94
    another
    0.82
     inning
    0.75
     Rainy
    0.72
     supermarket
    0.72
     tối
    0.72
    も含
    0.72
    printStackTrace
    0.72
    val
    0.72
    vors
    0.70
    Act Density 0.006%

    No Known Activations