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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash

    The neuron activates on tokens representing floating-point numbers (numeric literals containing a decimal point).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     wrist
    -0.06
    ffer
    -0.06
    manız
    -0.06
     vodka
    -0.06
     Я
    -0.06
    �乐
    -0.06
    koli
    -0.06
     consent
    -0.06
    rama
    -0.06
    iParam
    -0.06
    POSITIVE LOGITS
    .platform
    0.08
     Spider
    0.07
     نخست
    0.06
     theological
    0.06
     част
    0.06
    _offsets
    0.06
    .ret
    0.06
    hub
    0.06
     anarchists
    0.06
    _constants
    0.06
    Act Density 0.068%

    No Known Activations