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

    Neuronpedia

    INDEX
    Explanations

    recommendations or suggestions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     syntax
    0.76
     semantic
    0.72
     molecules
    0.71
     innate
    0.70
     explic
    0.68
     axons
    0.68
     fermions
    0.68
     coaxial
    0.67
     granularity
    0.67
     invented
    0.66
    POSITIVE LOGITS
     Nếu
    0.93
    future
    0.89
     future
    0.88
    下次
    0.82
     Jeśli
    0.81
     ખરી
    0.80
    whenever
    0.79
     nếu
    0.78
     toekomst
    0.78
     Recommend
    0.77
    Act Density 1.326%

    No Known Activations