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

    Neuronpedia

    INDEX
    Explanations

    Political correctness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -four
    -0.07
     Computational
    -0.07
    Girl
    -0.06
    lide
    -0.06
     usted
    -0.06
    rollment
    -0.06
     store
    -0.06
    Jack
    -0.06
    Anne
    -0.06
    Beth
    -0.06
    POSITIVE LOGITS
    .")↵
    0.06
     beast
    0.06
     foam
    0.06
    (balance
    0.06
     marketed
    0.06
    plib
    0.06
    .NoSuch
    0.06
    状况
    0.06
     張
    0.06
     BaseEntity
    0.06
    Act Density 0.032%

    No Known Activations