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

    Neuronpedia

    INDEX
    Explanations

    taken orally

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     from
    0.51
     about
    0.47
     for
    0.44
    ：
    0.44
     Alps
    0.43
     implying
    0.42
     WARRANTY
    0.42
    Α
    0.41
     yani
    0.40
     between
    0.40
    POSITIVE LOGITS
     കൂട
    0.50
     купи
    0.47
     ক্লিক
    0.47
    า
    0.47
     уеннары
    0.46
    amı
    0.45
     ਤ
    0.44
     পূরণ
    0.44
    <unused260>
    0.44
    स्कार
    0.44
    Act Density 0.010%

    No Known Activations