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

    Neuronpedia

    INDEX
    Explanations

    links to specific content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     अन्याय
    0.63
     教え
    0.55
     اکاؤنٹ
    0.55
    aurait
    0.54
    :=\
    0.53
    asadd
    0.53
    >());
    0.52
     স্বীক
    0.52
     предостав
    0.52
    huang
    0.52
    POSITIVE LOGITS
    ，「
    0.57
    '
    0.54
    為
    0.53
    れる
    0.52
    ，
    0.52
    其
    0.50
    吊
    0.50
    ‘
    0.49
     fed
    0.49
     tether
    0.49
    Act Density 0.000%

    No Known Activations