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

    Neuronpedia

    INDEX
    Explanations

    the followed by impact

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oretically
    1.11
    形势
    0.93
    скольку
    0.92
    কেবল
    0.91
     main
    0.90
     основным
    0.90
     आबादी
    0.90
     hanya
    0.89
     einzigen
    0.89
     only
    0.88
    POSITIVE LOGITS
     those
    0.88
     truly
    0.78
     beauty
    0.74
    those
    0.72
     Those
    0.72
    Those
    0.72
     Beauty
    0.70
    yarn
    0.68
    yat
    0.68
    VALUE
    0.68
    Act Density 0.036%

    No Known Activations