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

    Neuronpedia

    INDEX
    Explanations

    Project descriptions and coordination

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ascii
    -0.07
     Dictionary
    -0.07
    ening
    -0.07
    (prod
    -0.06
     quando
    -0.06
    ya
    -0.06
    (http
    -0.06
    *A
    -0.06
     була
    -0.06
     gia
    -0.06
    POSITIVE LOGITS
    .FullName
    0.08
    .smart
    0.07
    .generated
    0.07
    -awesome
    0.07
    ']."</
    0.06
     Рег
    0.06
    .dup
    0.06
     RANDOM
    0.06
    ครง
    0.06
    ','=
    0.06
    Act Density 0.009%

    No Known Activations