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

    Neuronpedia

    INDEX
    Explanations

    signals and instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     deleted
    -0.07
     Babies
    -0.07
     fontSize
    -0.06
     lives
    -0.06
    (version
    -0.06
    Career
    -0.06
     pymysql
    -0.06
     SIM
    -0.06
    stype
    -0.06
    anco
    -0.06
    POSITIVE LOGITS
     pública
    0.07
     enquanto
    0.07
    (+
    0.06
     ⌒
    0.06
    .</
    0.06
     بار
    0.06
     가까
    0.06
    状况
    0.06
    987
    0.06
    damn
    0.06
    Act Density 0.038%

    No Known Activations