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

    Neuronpedia

    INDEX
    Explanations

    starting with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Biotechnol
    0.44
    sm
    0.40
    -.
    0.40
    гатьох
    0.38
     Dalib
    0.38
     aktywn
    0.38
    snapshot
    0.37
    aco
    0.37
    acetamol
    0.37
     teaches
    0.37
    POSITIVE LOGITS
    ナー
    0.43
     го
    0.43
     तहे
    0.43
     най
    0.43
     ถ้า
    0.42
     lame
    0.42
     штра
    0.42
     hư
    0.42
    нер
    0.41
     срок
    0.41
    Act Density 0.000%

    No Known Activations