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

    Neuronpedia

    INDEX
    Explanations

    Technical problem-solving methods

    np_max-act · gemini-2.0-flash

    This neuron selectively activates on academic/technical terms that denote methods, approaches, paradigms, or other conceptual “research” constructs in scientific writing.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     недел
    -0.07
     temperatura
    -0.07
     ```
    -0.07
     níž
    -0.06
     Аз
    -0.06
    екотор
    -0.06
     needles
    -0.06
     Ecuador
    -0.06
    .':
    -0.06
     引
    -0.06
    POSITIVE LOGITS
    فاق
    0.07
     regiment
    0.07
     Sự
    0.07
     روابط
    0.06
    HING
    0.06
    _SCALE
    0.06
     condol
    0.06
    edReader
    0.06
     простран
    0.06
     amalg
    0.06
    Act Density 0.069%

    No Known Activations