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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    5
    0.64
    4
    0.59
     small
    0.57
    3
    0.54
     called
    0.54
     famous
    0.52
     who
    0.51
    Famous
    0.51
    9
    0.50
    2
    0.49
    POSITIVE LOGITS
    Ⲃ
    0.50
    程度の
    0.49
    ക്കുക
    0.48
    멱
    0.48
    ㄶ
    0.47
    軛
    0.46
     disbursements
    0.45
    限り
    0.45
     करो
    0.44
     wysokości
    0.44
    Act Density 0.001%

    No Known Activations