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

    Neuronpedia

    INDEX
    Explanations

    positioning oneself or entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ."),
    0.76
     It
    0.74
     পূরণ
    0.72
     But
    0.71
     and
    0.68
     Men
    0.66
     Have
    0.65
    wa
    0.64
    .")
    0.63
    enia
    0.61
    POSITIVE LOGITS
    که
    0.86
    ために
    0.80
    は
    0.78
    在
    0.78
    ٹ
    0.77
    ۔
    0.76
    ദ
    0.75
    ພວກເຮົາ
    0.73
    К
    0.73
    ни
    0.72
    Act Density 0.006%

    No Known Activations