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

    Neuronpedia

    INDEX
    Explanations

    side

    np_max-act · gemini-2.0-flash

    This neuron detects expressions referring to the “other side” of something (i.e. mentions of going to or being on the opposite side of a place).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Foo
    -0.07
    (<
    -0.07
     climbed
    -0.06
    .two
    -0.06
    -number
    -0.06
     Nora
    -0.06
     Hayden
    -0.06
    fv
    -0.06
    enqueue
    -0.06
     UPS
    -0.06
    POSITIVE LOGITS
    ymm
    0.06
     MMI
    0.06
    바이
    0.06
     turkey
    0.06
     modulo
    0.06
    '})↵
    0.06
    oader
    0.06
     datastore
    0.06
    _sess
    0.06
     último
    0.06
    Act Density 0.005%

    No Known Activations