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

    Neuronpedia

    INDEX
    Explanations

    moral/model

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    selen
    -0.08
    sole
    -0.08
     オ
    -0.08
     predefined
    -0.07
    available
    -0.07
    embedded
    -0.07
    [value
    -0.07
     REST
    -0.07
     spice
    -0.07
    [obj
    -0.07
    POSITIVE LOGITS
     Groei
    0.08
     गर्दै
    0.08
     страх
    0.08
     ҳисоб
    0.08
     cardinal
    0.08
    手续费
    0.08
    ಮಿ
    0.08
     yɛ
    0.08
     verdriet
    0.08
     samstar
    0.08
    Act Density 0.000%

    No Known Activations