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

    Neuronpedia

    INDEX
    Explanations

    Statements including "together"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    会发生
    -0.07
     genu
    -0.07
    itemName
    -0.07
    锖
    -0.06
    起重
    -0.06
     origen
    -0.06
    Orders
    -0.06
    INC
    -0.06
     Nes
    -0.06
     assignable
    -0.06
    POSITIVE LOGITS
    볓
    0.08
     altijd
    0.07
    kick
    0.07
    筅
    0.07
    uard
    0.07
    _LS
    0.07
    rika
    0.07
     Huckabee
    0.07
    䴘
    0.07
     weird
    0.07
    Act Density 0.035%

    No Known Activations