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

    Neuronpedia

    INDEX
    Explanations

    Jar

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _levels
    -0.07
    ompson
    -0.06
    正常
    -0.06
     Enlightenment
    -0.06
     змі
    -0.06
    EFF
    -0.06
     Aurora
    -0.06
    における
    -0.06
    ами
    -0.05
    letal
    -0.05
    POSITIVE LOGITS
     jar
    0.09
     Jar
    0.09
     jars
    0.09
    -star
    0.07
    jar
    0.07
    Marsh
    0.07
    Jar
    0.07
     appart
    0.07
    Ú
    0.07
     Jennings
    0.06
    Act Density 0.003%

    No Known Activations