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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    €¦
    0.83
    ށ
    0.66
    ί
    0.66
     уйнагыз
    0.63
    य़
    0.61
    €“
    0.59
    絴
    0.57
    ả
    0.56
    𝗸
    0.56
    <unused1720>
    0.55
    POSITIVE LOGITS
     "
    5.02
     “
    4.94
     ‘
    4.01
     '
    3.94
    「
    3.78
     „
    3.73
     «
    3.68
    “
    3.67
     “‘
    3.64
     「
    3.61
    Act Density 3.521%

    No Known Activations