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

    Neuronpedia

    INDEX
    Explanations

    javascript, package declarations, code comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     '
    -1.02
    -0.99
    出
    -0.98
    H
    -0.97
    d
    -0.97
    S
    -0.96
    ccccccc
    -0.96
    D
    -0.95
     aseguró
    -0.94
    N
    -0.94
    POSITIVE LOGITS
    Obr
    1.36
    Гер
    1.25
    삭제
    1.24
     novin
    1.20
    Kval
    1.16
    그리고
    1.16
    donde
    1.13
    Penjelasan
    1.09
    Aç
    1.09
    bkz
    1.09
    Act Density 0.008%

    No Known Activations