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

    Neuronpedia

    INDEX
    Explanations

    Informal writing/blog posts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    irected
    -0.07
    보기
    -0.06
     monarch
    -0.06
    moved
    -0.06
    236
    -0.06
    430
    -0.06
    .lex
    -0.06
     zie
    -0.06
    028
    -0.06
    229
    -0.06
    POSITIVE LOGITS
    Expense
    0.08
     Genetic
    0.06
    ایل
    0.06
    応
    0.06
    -machine
    0.06
    DOCKER
    0.06
    'é
    0.06
    -prepend
    0.06
     नई
    0.06
    -в
    0.06
    Act Density 0.030%

    No Known Activations