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

    Neuronpedia

    INDEX
    Explanations

    expense

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ATTACK
    -0.09
     Koop
    -0.09
     attack
    -0.08
     сопротив
    -0.08
     attaque
    -0.08
     Conway
    -0.08
     débats
    -0.08
     fabricants
    -0.08
     Craft
    -0.07
     Attack
    -0.07
    POSITIVE LOGITS
    voucher
    0.10
    Voucher
    0.10
     reimbursement
    0.09
     voucher
    0.09
    申
    0.09
    审批
    0.09
     refund
    0.08
    -approved
    0.08
    审核
    0.08
    -valid
    0.08
    Act Density 0.007%

    No Known Activations