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

    Neuronpedia

    INDEX
    Explanations

    thumbs up / thumbnail

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ∋
    0.49
    reson
    0.40
    𒌦
    0.39
     വിശ
    0.38
    소가
    0.38
    xygen
    0.38
     असामान्य
    0.38
    sparsity
    0.38
    дитесь
    0.38
    وزيع
    0.37
    POSITIVE LOGITS
     thumbs
    1.32
     thumb
    1.25
     Thumb
    1.12
    Thumb
    1.11
    thumbs
    1.05
    Thumbs
    1.02
    thumb
    0.99
    拇
    0.97
     thumbnail
    0.91
     thumbnails
    0.84
    Act Density 0.005%

    No Known Activations