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

    Neuronpedia

    INDEX
    Explanations

    traceback errors

    np_max-act · gemini-2.0-flash

    This neuron flags occurrences of Python exception or error names in traceback messages.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _FP
    -0.06
    ывать
    -0.06
    ToAdd
    -0.06
     البي
    -0.06
    文献
    -0.06
     horizontally
    -0.06
    باد
    -0.06
    clo
    -0.06
    (no
    -0.06
    ンピ
    -0.06
    POSITIVE LOGITS
     outright
    0.07
     матері
    0.07
     servants
    0.07
     Spotlight
    0.07
     लगभग
    0.07
     responseObject
    0.06
     Tanzania
    0.06
     getSize
    0.06
     próp
    0.06
     espaço
    0.06
    Act Density 0.000%

    No Known Activations