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

    Neuronpedia

    INDEX
    Explanations

    many of us

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ➔
    0.91
    つまり
    0.90
     giovane
    0.88
    viewModel
    0.88
     circumferential
    0.87
    frm
    0.87
    onChange
    0.86
    プール
    0.84
    짙
    0.84
    gte
    0.83
    POSITIVE LOGITS
    я
    0.77
    িত
    0.77
     works
    0.75
    0.74
    𝘬
    0.72
    uş
    0.71
    ோ
    0.71
    ヤー
    0.70
    šky
    0.70
     son
    0.68
    Act Density 0.001%

    No Known Activations