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

    Neuronpedia

    INDEX
    Explanations

    breakdown into categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    o
    0.94
    gies
    0.88
    y
    0.88
    g
    0.87
    ம்
    0.83
    ദി
    0.82
    gie
    0.80
     розташо
    0.79
    gres
    0.79
    د
    0.78
    POSITIVE LOGITS
    .\
    1.13
    .…
    1.03
    .[
    1.00
    —.
    0.98
    ।.
    0.94
     excerpts
    0.94
     mism
    0.92
    čnom
    0.91
    .";
    0.90
     nigris
    0.90
    Act Density 0.103%

    No Known Activations