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

    Neuronpedia

    INDEX
    Explanations

    daughter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Kh
    -0.07
     KUR
    -0.07
     Bas
    -0.07
     selecion
    -0.06
     Uganda
    -0.06
     hashmap
    -0.06
    -light
    -0.06
     persuasion
    -0.06
     EDT
    -0.06
     mse
    -0.06
    POSITIVE LOGITS
    ondrous
    0.07
    时代
    0.06
     youth
    0.06
    书
    0.06
     instantiated
    0.06
    equality
    0.06
    owment
    0.06
    AREN
    0.06
    constructed
    0.06
     fifty
    0.06
    Act Density 0.005%

    No Known Activations