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

    Neuronpedia

    INDEX
    Explanations

    k

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (prod
    -0.08
    _INSTANCE
    -0.07
    ()==
    -0.07
    防治
    -0.07
    rounded
    -0.07
    老年
    -0.07
    _SID
    -0.07
    为民
    -0.07
    南山
    -0.07
    +"'
    -0.07
    POSITIVE LOGITS
     Participants
    0.07
    万科
    0.07
     outraged
    0.06
     Unlimited
    0.06
    ווי
    0.06
     Imp
    0.06
    דון
    0.06
     salaries
    0.06
     ripping
    0.06
    faction
    0.06
    Act Density 0.009%

    No Known Activations