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

    Neuronpedia

    INDEX
    Explanations

    passed, elected, results, announced

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    During
    0.64
     durante
    0.53
     During
    0.52
    during
    0.48
     during
    0.47
    യ്യ
    0.46
    Markup
    0.46
    то
    0.46
    бата
    0.45
    ISTR
    0.45
    POSITIVE LOGITS
     SPECT
    0.52
     Vogue
    0.50
     Deadline
    0.49
     Senado
    0.49
     GL
    0.49
     Mirage
    0.48
     n
    0.48
     superstar
    0.48
     Mesmo
    0.48
     Bangladesh
    0.47
    Act Density 0.015%

    No Known Activations