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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Fields
    -0.07
    .black
    -0.07
    ैत
    -0.07
     Nodes
    -0.07
    _accounts
    -0.06
    events
    -0.06
     onay
    -0.06
    eenth
    -0.06
     whereby
    -0.06
     ListNode
    -0.06
    POSITIVE LOGITS
     worry
    0.08
    ゴ
    0.07
    驶
    0.06
    exo
    0.06
     hamburg
    0.06
     cruising
    0.06
     mệ
    0.06
    .plan
    0.06
    선
    0.06
     下载
    0.06
    Act Density 0.003%

    No Known Activations