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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     было
    -0.08
    (balance
    -0.07
    paid
    -0.07
    curacy
    -0.07
    vertime
    -0.07
     PURE
    -0.07
    휄
    -0.07
    ilton
    -0.07
    ffffffff
    -0.06
     Luke
    -0.06
    POSITIVE LOGITS
     aşağı
    0.07
    鉴定
    0.07
     Scholar
    0.07
     spike
    0.07
     molding
    0.07
     network
    0.07
    .News
    0.07
     رسول
    0.06
     Arch
    0.06
    =create
    0.06
    Act Density 0.025%

    No Known Activations