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

    Neuronpedia

    INDEX
    Explanations

    defining terms in writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     conservatism
    -0.08
    �
    -0.07
    교
    -0.06
    �性
    -0.06
    础
    -0.06
     jov
    -0.06
    商铺
    -0.06
     uniformly
    -0.06
    structures
    -0.06
     cyc
    -0.06
    POSITIVE LOGITS
     szkoły
    0.07
    .ids
    0.07
    -'+
    0.07
     ממנו
    0.07
    -feedback
    0.07
    所做的
    0.07
    -bo
    0.07
    (↵
    0.07
     chefs
    0.07
    -"+
    0.06
    Act Density 0.017%

    No Known Activations