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

    Neuronpedia

    INDEX
    Explanations

    confronting the reality of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    号码
    0.60
    错误
    0.59
    错误的
    0.57
     dSample
    0.54
     dữ
    0.53
     chiffres
    0.53
    buttonLevel
    0.52
     puedas
    0.51
     newApproved
    0.51
    犃
    0.50
    POSITIVE LOGITS
     (
    0.61
    (
    0.59
    .
    0.50
    -
    0.49
    isim
    0.48
     burgeoning
    0.47
    ination
    0.46
    September
    0.46
    /
    0.46
    จ
    0.46
    Act Density 0.004%

    No Known Activations