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

    Neuronpedia

    INDEX
    Explanations

    curse and blessing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Navbar
    1.08
    wl
    1.01
    कृष्ण
    1.00
    arity
    0.99
    엎
    0.97
    opie
    0.96
    même
    0.93
    $[\
    0.92
    ,$$
    0.88
    }],
    0.88
    POSITIVE LOGITS
    𝐫
    1.22
    у
    1.21
    ي
    1.15
    ان
    1.14
     troubled
    1.13
    лей
    1.11
    ровой
    1.05
    iyor
    1.03
     водой
    1.02
    ্লোক
    1.02
    Act Density 0.053%

    No Known Activations