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

    Neuronpedia

    INDEX
    Explanations

    Code related

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reserve
    -0.07
     regression
    -0.07
     isot
    -0.07
     linear
    -0.07
    Eastern
    -0.06
     extreme
    -0.06
    _female
    -0.06
     обо
    -0.06
     creep
    -0.06
    standard
    -0.06
    POSITIVE LOGITS
     onsite
    0.06
    UIFont
    0.06
    _SCRIPT
    0.06
     configFile
    0.06
    /kg
    0.06
     öğret
    0.06
    .Br
    0.06
     вв
    0.06
    loff
    0.06
     INCIDENTAL
    0.06
    Act Density 0.099%

    No Known Activations