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

    Neuronpedia

    INDEX
    Explanations

    plan

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of bankruptcy reorganization plans and their confirmation (e.g. “Plan,” “reorganization,” “confirm,” “confirmation”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    VALUE
    -0.06
    	location
    -0.06
     mess
    -0.06
     repetition
    -0.06
     stranger
    -0.06
    .words
    -0.06
    estructor
    -0.06
    Pa
    -0.06
    .entry
    -0.06
    _FLAG
    -0.06
    POSITIVE LOGITS
     قدر
    0.08
    体系
    0.07
    celona
    0.07
    LLL
    0.07
     Evet
    0.07
     öden
    0.07
    logg
    0.07
     programu
    0.06
    .getMin
    0.06
     Kentucky
    0.06
    Act Density 0.001%

    No Known Activations