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

    Neuronpedia

    INDEX
    Explanations

    code comments

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Title
    0.73
    タイトル
    0.72
     dhad
    0.72
    지컬
    0.69
     최
    0.68
    走り
    0.68
     زیرمه
    0.67
    ইতি
    0.67
     له
    0.67
    标题
    0.67
    POSITIVE LOGITS
     wę
    0.82
     prepare
    0.71
    animals
    0.64
    ausal
    0.63
     navigate
    0.61
     prepared
    0.59
     animals
    0.59
     முன்
    0.59
     Viktor
    0.58
    εργ
    0.58
    Act Density 0.004%

    No Known Activations