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

    Neuronpedia

    INDEX
    Explanations

    architectures or code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     temos
    0.52
     verkl
    0.51
     abstra
    0.51
     grote
    0.50
     haremos
    0.49
     hyvin
    0.48
     hemos
    0.47
     errone
    0.46
     tek
    0.46
    Ọ
    0.45
    POSITIVE LOGITS
    ator
    0.50
     журнали
    0.47
     Бел
    0.47
    ators
    0.47
     анализ
    0.46
    е
    0.43
    кан
    0.43
     кри
    0.43
    cura
    0.43
    лен
    0.42
    Act Density 0.001%

    No Known Activations