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

    Neuronpedia

    INDEX
    Explanations

    options and recommendations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ۰۰
    0.90
     máximo
    0.87
    стью
    0.85
     máxima
    0.82
     necessario
    0.81
    skirts
    0.78
    ூன்
    0.75
     massimo
    0.74
    合理
    0.73
    maximum
    0.72
    POSITIVE LOGITS
    👍
    1.07
     👍
    1.06
     👌
    1.03
     IMO
    1.00
    👌
    0.88
     сочета
    0.87
     circumstantial
    0.86
     IMHO
    0.86
     imo
    0.85
     overall
    0.83
    Act Density 0.306%

    No Known Activations