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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash

    This neuron activates on numerical measurement values—especially decimal numbers—in data‐collection and refinement summaries.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Blade
    -0.07
    oksen
    -0.07
     Colo
    -0.07
    回答
    -0.07
    нуться
    -0.07
     Quran
    -0.06
    797
    -0.06
    empo
    -0.06
     Nou
    -0.06
     Af
    -0.06
    POSITIVE LOGITS
    Vec
    0.07
    _vec
    0.06
    nia
    0.06
     \|
    0.06
    iyor
    0.06
    威
    0.06
     stab
    0.06
    لوب
    0.06
    娱乐
    0.06
     stě
    0.06
    Act Density 0.000%

    No Known Activations