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

    Neuronpedia

    INDEX
    Explanations

    gospel

    np_max-act · gemini-2.0-flash

    The neuron reliably lights up on occurrences of the word “gospel” (and its close variants like “Gospels”) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     کاربر
    -0.08
     staring
    -0.07
     newArray
    -0.07
    Two
    -0.07
    		    ↵
    -0.07
     arbitrary
    -0.07
    -0.06
     brick
    -0.06
    '^
    -0.06
     Clair
    -0.06
    POSITIVE LOGITS
     Gospel
    0.12
     gospel
    0.11
     evangel
    0.09
     Evangel
    0.09
    па
    0.07
    devil
    0.07
     swelling
    0.07
    ospels
    0.07
    _vol
    0.07
    ospel
    0.07
    Act Density 0.002%

    No Known Activations