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

    Neuronpedia

    INDEX
    Explanations

    degrees

    np_max-act · gemini-2.0-flash

    This neuron never activates—it does not detect any pattern in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ğitim
    -0.07
    册
    -0.07
    _old
    -0.07
     Kazakhstan
    -0.06
     Syn
    -0.06
     CIT
    -0.06
    尿
    -0.06
     گن
    -0.06
    Syn
    -0.06
    742
    -0.06
    POSITIVE LOGITS
     outdoors
    0.07
     degrees
    0.07
     SCORE
    0.07
    press
    0.06
    energy
    0.06
     deut
    0.06
     подв
    0.06
     color
    0.06
    oug
    0.06
     Wes
    0.06
    Act Density 0.005%

    No Known Activations