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

    Neuronpedia

    INDEX
    Explanations

    initial-scale

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AMINATION
    0.45
     grise
    0.43
    ژی
    0.43
    ailleurs
    0.40
    спубли
    0.40
     methylation
    0.40
     acetylation
    0.39
    イレ
    0.39
    鷄
    0.39
    orgung
    0.39
    POSITIVE LOGITS
     viewport
    0.77
    viewport
    0.76
     width
    0.69
    width
    0.68
     initial
    0.62
    Viewport
    0.62
    meta
    0.62
     meta
    0.61
     Width
    0.59
     initially
    0.59
    Act Density 0.007%

    No Known Activations