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

    Neuronpedia

    INDEX
    Explanations

    modelmodel numbers and serials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    बीयत
    0.42
     andRow
    0.42
     dépassant
    0.42
     இயற்க
    0.42
     UserModel
    0.42
     Gazprom
    0.41
    헙
    0.40
     slashing
    0.40
    와이스
    0.40
     reigning
    0.40
    POSITIVE LOGITS
    6
    0.75
    5
    0.71
    9
    0.68
    3
    0.68
    1
    0.68
    7
    0.67
    2
    0.64
    8
    0.64
    4
    0.63
    J
    0.52
    Act Density 0.009%

    No Known Activations