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

    Neuronpedia

    INDEX
    Explanations

    specific aspect / behavior

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nagyon
    1.59
     labai
    1.54
     polinom
    1.50
     interfaz
    1.49
    Tidak
    1.47
    ूतक
    1.45
    ໃຊ
    1.44
     strumento
    1.44
     puoi
    1.43
     enggak
    1.43
    POSITIVE LOGITS
     and
    1.39
    and
    1.20
     (
    1.17
     (“
    1.12
     or
    0.97
    -
    0.97
     以及
    0.96
     such
    0.94
    以及
    0.94
    .
    0.93
    Act Density 0.212%

    No Known Activations