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

    Neuronpedia

    INDEX
    Explanations

    darklords and collected regrets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    運動
    0.46
     longitudinal
    0.43
    ...+
    0.42
    網絡
    0.42
     letting
    0.42
    +(-
    0.41
     subir
    0.40
    ες
    0.40
     ρο
    0.40
    Código
    0.40
    POSITIVE LOGITS
     eloquently
    0.51
    സാ
    0.49
     amply
    0.48
    anno
    0.47
    t
    0.46
    کیل
    0.46
     powerfully
    0.46
     ably
    0.46
     abhor
    0.44
     Valentines
    0.44
    Act Density 0.047%

    No Known Activations