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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    The neuron is triggered by numeric literals with decimal points (floating-point numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Essentially
    -0.07
     classic
    -0.07
     conditional
    -0.07
     classics
    -0.07
    olor
    -0.07
    adders
    -0.06
     oppressed
    -0.06
    043
    -0.06
    RB
    -0.06
    LPARAM
    -0.06
    POSITIVE LOGITS
     dane
    0.07
     đứ
    0.07
     곧
    0.06
    ').'
    0.06
     erre
    0.06
     wart
    0.06
    니스
    0.06
     восстанов
    0.06
     گذ
    0.06
    /j
    0.06
    Act Density 0.055%

    No Known Activations