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

    Neuronpedia

    INDEX
    Explanations

    difference, distinction, lack

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    springboot
    0.41
    转型
    0.41
     simbolo
    0.39
    <0x10>
    0.38
    سون
    0.38
     individuais
    0.38
    ghed
    0.37
    oru
    0.37
    Condensed
    0.36
    تج
    0.36
    POSITIVE LOGITS
     tendency
    0.93
     difference
    0.85
     need
    0.85
     disconnect
    0.82
     dearth
    0.80
     discrepancy
    0.77
     paucity
    0.75
     shortage
    0.75
     disparity
    0.75
     prevalence
    0.72
    Act Density 0.016%

    No Known Activations