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

    Neuronpedia

    INDEX
    Explanations

    examples within lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝗲
    3.22
    ்
    2.99
    ी
    2.90
    𝗶
    2.85
    𝗮
    2.76
     prostřed
    2.71
    𝗹
    2.69
    𝗼
    2.69
    ো
    2.68
    er
    2.65
    POSITIVE LOGITS
    en
    3.09
     OnInit
    3.05
    ate
    2.78
     manifold
    2.75
    А
    2.71
     immunoblot
    2.65
    телей
    2.64
    nesday
    2.57
     manifolds
    2.57
     annulus
    2.56
    Act Density 0.104%

    No Known Activations