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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kaydet
    -0.07
    _depend
    -0.06
     cont
    -0.06
     agency
    -0.06
    subscriptions
    -0.06
    portlet
    -0.06
    dings
    -0.06
     Flem
    -0.06
    (skb
    -0.06
     xOffset
    -0.06
    POSITIVE LOGITS
     О
    0.07
     PS
    0.07
    texto
    0.06
     کنید
    0.06
     femmes
    0.06
    .Session
    0.06
    \v
    0.06
     violates
    0.06
     وات
    0.06
    .PR
    0.06
    Act Density 0.029%

    No Known Activations