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

    Neuronpedia

    INDEX
    Explanations

    when or if someone does

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     circumstantial
    0.40
    気の
    0.40
    ลล์
    0.38
     thrives
    0.37
     subscribed
    0.37
    英寸
    0.37
     likes
    0.37
     ভাষ
    0.36
    和谐
    0.36
     downstream
    0.36
    POSITIVE LOGITS
    聽到
    0.68
     someone
    0.67
    听到
    0.66
    someone
    0.66
    看到
    0.65
     somebody
    0.64
    有人
    0.61
     Someone
    0.59
     услы
    0.58
     zobac
    0.58
    Act Density 0.004%

    No Known Activations