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

    Neuronpedia

    INDEX
    Explanations

    red

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     осіб
    0.49
    ও
    0.46
    6
    0.45
    рів
    0.44
    蝟
    0.43
    이는
    0.43
    ட
    0.43
     bactéries
    0.43
    이어
    0.42
     পরিস্থিত
    0.41
    POSITIVE LOGITS
    ва
    0.58
    t
    0.57
     I
    0.49
     an
    0.48
    ı
    0.47
    ある
    0.46
    red
    0.46
    se
    0.46
    tt
    0.45
     با
    0.45
    Act Density 0.057%

    No Known Activations