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

    Neuronpedia

    INDEX
    Explanations

    por lo que

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    我
    0.65
    in
    0.50
     вопро
    0.50
    意见
    0.49
    ında
    0.47
    有
    0.46
    Sprite
    0.45
    在
    0.45
    𝐞
    0.45
     ассорти
    0.44
    POSITIVE LOGITS
     tr
    0.49
     zari
    0.48
     samping
    0.47
     construct
    0.46
     sequenced
    0.46
     drizz
    0.45
     Nen
    0.45
     डिन
    0.45
     balsamic
    0.45
     facile
    0.44
    Act Density 0.000%

    No Known Activations