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

    Neuronpedia

    INDEX
    Explanations

    code configuration files

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    🐆
    -0.08
    龠
    -0.07
    人才培养
    -0.07
    鬓
    -0.07
     person
    -0.07
    cai
    -0.07
    extension
    -0.07
     altercation
    -0.07
    .directive
    -0.07
    checkout
    -0.06
    POSITIVE LOGITS
     الكر
    0.08
    .blank
    0.07
    陕西省
    0.07
     clocks
    0.07
    cents
    0.07
    һ
    0.07
    年下半年
    0.06
    зав
    0.06
     LEFT
    0.06
     primitives
    0.06
    Act Density 0.003%

    No Known Activations