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

    Neuronpedia

    INDEX
    Explanations

    code definition keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ايجاد
    0.40
     방법에
    0.40
     uncover
    0.38
     zrobi
    0.38
    ʋ
    0.38
     MEAN
    0.38
     furiously
    0.38
    ্জন
    0.38
    緖
    0.38
    fileExistsAtPath
    0.37
    POSITIVE LOGITS
     William
    0.38
     Cumberland
    0.38
     Dated
    0.37
    íncipe
    0.36
    assed
    0.36
     Wentworth
    0.36
     Amor
    0.36
     Sanit
    0.36
     Colby
    0.36
    лки
    0.36
    Act Density 0.019%

    No Known Activations