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

    Neuronpedia

    INDEX
    Explanations

    more

    np_max-act · gemini-2.0-flash

    The neuron is detecting floating-point number tokens (i.e. decimal numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    자를
    -0.07
    ählt
    -0.06
    -person
    -0.06
     جوان
    -0.06
     therapies
    -0.06
    .www
    -0.06
    …ط
    -0.06
     Remain
    -0.06
    /gtest
    -0.06
     Liebe
    -0.06
    POSITIVE LOGITS
     more
    0.07
     unin
    0.06
     WebSocket
    0.06
    NOWLED
    0.06
     circ
    0.06
     exec
    0.06
    nowled
    0.06
     onDelete
    0.06
     Moj
    0.06
    _dim
    0.06
    Act Density 0.034%

    No Known Activations