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

    Neuronpedia

    INDEX
    Explanations

    Scott

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    培
    -0.07
     バ
    -0.07
     Yaş
    -0.07
     derivative
    -0.06
     vib
    -0.06
     Lump
    -0.06
     Stap
    -0.06
     GAM
    -0.06
    hop
    -0.06
     LH
    -0.06
    POSITIVE LOGITS
     Scott
    0.25
    Scott
    0.22
     Scottish
    0.09
    cott
    0.09
    OTT
    0.09
    Todd
    0.08
     Scots
    0.08
     Scotland
    0.08
    /rfc
    0.08
     Todd
    0.08
    Act Density 0.005%

    No Known Activations