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

    Neuronpedia

    INDEX
    Explanations

    approximations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    关心
    -0.07
    llib
    -0.07
    -reference
    -0.07
     Written
    -0.06
    pec
    -0.06
    Ŗ
    -0.06
    .rcParams
    -0.06
    uent
    -0.06
     policy
    -0.06
    嬥
    -0.06
    POSITIVE LOGITS
     Zap
    0.08
     chop
    0.07
     Onc
    0.07
     attacks
    0.07
     المح
    0.07
     setLocation
    0.07
    ところ
    0.07
     BigNumber
    0.07
     Searching
    0.07
     overpower
    0.07
    Act Density 0.030%

    No Known Activations