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

    Neuronpedia

    INDEX
    Explanations

    now, after explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    том
    0.97
     Chair
    0.88
    Chair
    0.83
    uir
    0.82
    iet
    0.80
    Republic
    0.79
    object
    0.77
     kursi
    0.77
     Paragraph
    0.76
    アイ
    0.76
    POSITIVE LOGITS
     causa
    0.77
     flyers
    0.73
     dû
    0.72
     codecs
    0.72
     payers
    0.71
     Ny
    0.70
     effecting
    0.68
     skyrocketed
    0.68
    hasNext
    0.67
    nyc
    0.67
    Act Density 0.000%

    No Known Activations