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

    Neuronpedia

    INDEX
    Explanations

    's

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    exclusive
    -0.08
    agedList
    -0.07
    ترین
    -0.07
     Losing
    -0.07
    Compet
    -0.07
     campaign
    -0.07
     snaps
    -0.07
    LEFT
    -0.07
    avg
    -0.06
     Free
    -0.06
    POSITIVE LOGITS
     너무
    0.06
    instance
    0.06
    ,end
    0.06
     пес
    0.06
     tato
    0.06
    olvable
    0.06
     userEmail
    0.06
    页面存档备份
    0.06
     هج
    0.06
    见
    0.05
    Act Density 0.555%

    No Known Activations