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

    Neuronpedia

    INDEX
    Explanations

    as

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :no
    -0.07
    _dir
    -0.07
     request
    -0.07
    pic
    -0.06
     specific
    -0.06
     Start
    -0.06
    _listen
    -0.06
    /be
    -0.06
     "@
    -0.06
     starts
    -0.06
    POSITIVE LOGITS
    Greek
    0.07
    _body
    0.07
     věci
    0.07
     Rentals
    0.07
     bestellen
    0.06
     zastup
    0.06
     hardcoded
    0.06
     Deng
    0.06
     Gluten
    0.06
    충
    0.06
    Act Density 0.030%

    No Known Activations