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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Removed
    -0.08
     mbox
    -0.06
     originals
    -0.06
     yoksa
    -0.06
     号
    -0.06
    CHK
    -0.06
     форме
    -0.06
    ��
    -0.06
     kijken
    -0.06
    _SEP
    -0.06
    POSITIVE LOGITS
    ---</
    0.07
     Demand
    0.07
     undercover
    0.06
     göz
    0.06
     Bis
    0.06
    �
    0.06
    �다
    0.06
     perk
    0.06
    鞋
    0.06
    .next
    0.06
    Act Density 0.022%

    No Known Activations