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

    Neuronpedia

    INDEX
    Explanations

    Paper

    np_max-act · gemini-2.0-flash

    This neuron activates on floating-point numeric literals (numbers containing a decimal point).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     �
    -0.06
     Impl
    -0.06
     تومان
    -0.06
     理
    -0.06
     上涨
    -0.06
     облад
    -0.06
    Genesis
    -0.06
    雷
    -0.06
     Balanced
    -0.06
     Κυ
    -0.06
    POSITIVE LOGITS
    pb
    0.07
    <section
    0.06
    melon
    0.06
     Cooke
    0.06
    typeof
    0.06
    ('/',
    0.06
     Marks
    0.06
    chers
    0.06
    Pedido
    0.06
    _trim
    0.06
    Act Density 0.279%

    No Known Activations