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

    Neuronpedia

    INDEX
    Explanations

    listing transition words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     conco
    0.55
    fool
    0.54
    guien
    0.51
    ীবনী
    0.49
    Przyp
    0.49
    Nuestro
    0.49
    Prothorax
    0.49
     ಪೊ
    0.49
    ineux
    0.49
    ómetro
    0.48
    POSITIVE LOGITS
    但是
    0.75
     However
    0.74
     however
    0.73
     但是
    0.65
    However
    0.64
     but
    0.62
    しかし
    0.61
     그러나
    0.60
    但是在
    0.59
     tetapi
    0.58
    Act Density 0.008%

    No Known Activations