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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash

    code snippets related to manipulating lists in Python.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron strongly fires on the literal token “python,” especially when it’s used as a code‐block language tag.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    orious
    -0.06
    IRM
    -0.06
     schö
    -0.06
    ANI
    -0.06
     petitions
    -0.06
    ereo
    -0.06
     Francisco
    -0.06
     erfolgreich
    -0.06
    ollapsed
    -0.06
     tender
    -0.06
    POSITIVE LOGITS
    七
    0.07
    _MED
    0.06
    xAD
    0.06
     обол
    0.06
     کر
    0.06
    벨
    0.06
     hasher
    0.06
    д
    0.06
     transmit
    0.06
     عش
    0.06
    Act Density 0.039%

    No Known Activations