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

    Neuronpedia

    INDEX
    Explanations

    from ... to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    $),
    0.49
    сія
    0.43
    accepted
    0.42
    filed
    0.41
    nsic
    0.41
     मच्छ
    0.41
    Masters
    0.40
    стика
    0.40
    ⃝
    0.39
    Zoom
    0.38
    POSITIVE LOGITS
     emerge
    0.52
     sweep
    0.50
     Ellington
    0.49
     молодо
    0.47
     மீண்டும்
    0.47
     emerges
    0.46
    ᄈ
    0.46
     rad
    0.45
     escap
    0.45
     вновь
    0.45
    Act Density 0.001%

    No Known Activations