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

    Neuronpedia

    INDEX
    Explanations

    is a recommendation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     inversely
    0.86
     techniques
    0.85
     technique
    0.77
     Techniques
    0.77
     graded
    0.76
     maneiras
    0.75
     Technique
    0.74
     simpler
    0.74
     unpredictable
    0.73
     greater
    0.73
    POSITIVE LOGITS
     considerado
    0.82
     consideradas
    0.77
     considerados
    0.76
    寘
    0.73
    刚好
    0.73
     माना
    0.70
    涵盖
    0.69
    Consider
    0.69
     atuação
    0.68
     দিয়েছিলেন
    0.68
    Act Density 0.297%

    No Known Activations