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

    Neuronpedia

    INDEX
    Explanations

    Computer hardware/servers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     induces
    -0.08
    |.
    -0.07
     indicative
    -0.07
    弭
    -0.07
    .getOrder
    -0.07
    <select
    -0.06
     Surrey
    -0.06
     Bid
    -0.06
    -turned
    -0.06
    isser
    -0.06
    POSITIVE LOGITS
    服饰
    0.07
     Gaza
    0.07
     manipulation
    0.07
    颟
    0.07
     yoga
    0.07
     unpleasant
    0.07
     SLOT
    0.07
     đọc
    0.06
     טוען
    0.06
     Vegan
    0.06
    Act Density 0.022%

    No Known Activations