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

    Neuronpedia

    INDEX
    Explanations

    18

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _website
    -0.07
     gradu
    -0.06
    boxes
    -0.06
     posto
    -0.06
    }\\
    -0.06
     Sleep
    -0.06
    ocused
    -0.06
     Consulting
    -0.06
     nye
    -0.06
     expectancy
    -0.06
    POSITIVE LOGITS
    ']");↵
    0.07
    /
↵
↵
    0.07
    _offer
    0.07
     Dar
    0.07
     كام
    0.06
     dří
    0.06
    řízení
    0.06
     Ně
    0.06
    测
    0.06
    ’’
    0.06
    Act Density 0.011%

    No Known Activations