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

    Neuronpedia

    INDEX
    Explanations

    numbers and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    buyers
    0.43
    usable
    0.42
    userId
    0.40
    inter
    0.39
    know
    0.39
    rec
    0.38
     rec
    0.37
     chose
    0.37
    arte
    0.37
    accessible
    0.37
    POSITIVE LOGITS
    的过程中
    0.45
    脱毛
    0.45
    ഭ്യാസ
    0.44
     strenuous
    0.43
    镖
    0.42
     Марафон
    0.42
     transformação
    0.41
     افزایش
    0.41
     SUBSTITUTE
    0.39
    妣
    0.39
    Act Density 0.004%

    No Known Activations