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

    Neuronpedia

    INDEX
    Explanations

    кры/кри/kry/kri

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    荭
    0.45
    untar
    0.44
     suma
    0.42
     сумма
    0.42
     unary
    0.42
    ार्किक
    0.41
    ંત્ર
    0.40
    适当
    0.40
    Unary
    0.39
     libera
    0.39
    POSITIVE LOGITS
     кры
    0.65
     кри
    0.64
     Kry
    0.63
     kry
    0.61
    ształ
    0.58
    ття
    0.56
     Кры
    0.53
     kri
    0.52
     Kri
    0.52
    Cri
    0.51
    Act Density 0.001%

    No Known Activations