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

    Neuronpedia

    INDEX
    Explanations

    names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    kdir
    -0.07
     Τ
    -0.07
     पक
    -0.06
    lever
    -0.06
     FName
    -0.06
     trending
    -0.06
    athroom
    -0.06
     Aydın
    -0.06
     गलत
    -0.06
     glaring
    -0.06
    POSITIVE LOGITS
    首页
    0.07
     Gary
    0.06
    Ack
    0.06
    [{
    0.06
     Für
    0.06
     Div
    0.06
     DECLARE
    0.06
     salaries
    0.06
     measles
    0.06
     Docs
    0.06
    Act Density 0.046%

    No Known Activations