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

    Neuronpedia

    INDEX
    Explanations

    perspectives, topics, subject matter

    np_max-act · gemini-2.0-flash

    The neuron activates primarily on tokens representing decimal (floating-point) numbers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     track
    -0.06
     xa
    -0.06
     peach
    -0.06
    -connected
    -0.06
     deepcopy
    -0.06
    anj
    -0.06
    _study
    -0.06
    -CP
    -0.06
    example
    -0.06
     Jack
    -0.06
    POSITIVE LOGITS
    ữa
    0.07
    ôle
    0.07
    alten
    0.06
     nouvel
    0.06
     бел
    0.06
    \View
    0.06
    Ю
    0.06
    players
    0.06
     marty
    0.06
     Duo
    0.06
    Act Density 0.072%

    No Known Activations