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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wides
    -0.08
    .getColor
    -0.07
    387
    -0.07
     Deutschland
    -0.06
     dwar
    -0.06
    322
    -0.06
     retorna
    -0.06
     ztr
    -0.06
    /TR
    -0.06
     angels
    -0.06
    POSITIVE LOGITS
    렸
    0.07
     fray
    0.06
    いの
    0.06
    ้ท
    0.06
    Exist
    0.06
     owes
    0.06
    theValue
    0.06
     Apply
    0.06
     Мі
    0.06
     dumpsters
    0.05
    Act Density 0.007%

    No Known Activations