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

    Neuronpedia

    INDEX
    Explanations

    heat, transfer, Odawara, Reuters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    珑
    0.73
    桠
    0.68
    might
    0.67
    Mad
    0.66
     Rồi
    0.65
    ਉਣ
    0.62
    瓏
    0.61
    有一种
    0.61
    Mapped
    0.61
    )+(
    0.61
    POSITIVE LOGITS
    エントリー
    0.63
     Strictly
    0.61
    Dis
    0.57
    रसा
    0.56
     supre
    0.53
     श्र
    0.52
     []);
    0.52
     Henson
    0.51
     Cannot
    0.51
     Hicks
    0.51
    Act Density 0.107%

    No Known Activations