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

    Neuronpedia

    INDEX
    Explanations

    treason

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    FlowLayout
    -0.08
     όμως
    -0.07
    ิสต
    -0.07
    ัฒน
    -0.07
    Database
    -0.07
    alsa
    -0.07
    uestra
    -0.07
    _coupon
    -0.07
    oplay
    -0.06
    ба
    -0.06
    POSITIVE LOGITS
     treason
    0.10
     induction
    0.07
    *=*=
    0.06
    RODUCTION
    0.06
     contrib
    0.06
     Withdraw
    0.06
     Revolution
    0.06
     diplomatic
    0.06
    .MESSAGE
    0.06
    (shape
    0.06
    Act Density 0.004%

    No Known Activations