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

    Neuronpedia

    INDEX
    Explanations

    company financial reports

    np_max-act · gemini-2.0-flash

    This neuron selectively activates on decimal‐formatted numeric tokens (i.e. floating‐point numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     shameful
    -0.06
     freund
    -0.06
     pů
    -0.06
    طور
    -0.06
    Чер
    -0.06
    처
    -0.06
     QApplication
    -0.06
    ��제
    -0.06
    کی
    -0.06
    Sh
    -0.06
    POSITIVE LOGITS
     tiers
    0.07
     ド
    0.07
    wagon
    0.07
     nghề
    0.06
     Mechanics
    0.06
     exploding
    0.06
    101
    0.06
     cater
    0.06
     realistic
    0.06
     tier
    0.06
    Act Density 0.024%

    No Known Activations