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

    Neuronpedia

    INDEX
    Explanations

    following "the"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     textual
    0.65
    环境中
    0.63
    ֛
    0.62
     certainty
    0.61
     contextual
    0.61
    条件下
    0.60
     elección
    0.60
     presenza
    0.59
     unmet
    0.59
     rámci
    0.59
    POSITIVE LOGITS
     playoffs
    0.71
    movies
    0.68
    backend
    0.65
     Movies
    0.64
     Holidays
    0.63
     maak
    0.63
     woodwork
    0.63
    Movies
    0.62
     movies
    0.62
     ropes
    0.61
    Act Density 0.147%

    No Known Activations