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

    Neuronpedia

    INDEX
    Explanations

    in/on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cerr
    -0.06
     interacting
    -0.06
    「お
    -0.06
     Vin
    -0.06
     res
    -0.06
    テ
    -0.06
     touchdowns
    -0.06
     ochran
    -0.06
     developed
    -0.06
     aumento
    -0.06
    POSITIVE LOGITS
     confusing
    0.07
    ắc
    0.07
    574
    0.07
     Fisher
    0.07
     Hopefully
    0.07
    izont
    0.07
     Kolkata
    0.07
    57
    0.06
     Gore
    0.06
    ۳۵
    0.06
    Act Density 0.128%

    No Known Activations