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

    Neuronpedia

    INDEX
    Explanations

    Living spaces

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of extra or auxiliary living spaces (e.g. “studio,” “apartment,” “bonus room,” “workshop,” or “lower level” areas).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Gap
    -0.07
     fireworks
    -0.07
    Blog
    -0.06
    ิธ
    -0.06
    .Flow
    -0.06
    ToFront
    -0.06
     Highland
    -0.06
     exams
    -0.06
    دی
    -0.06
     nause
    -0.06
    POSITIVE LOGITS
     tamamen
    0.07
     όλ
    0.07
    >↵↵
    0.06
     entrepreneurship
    0.06
    .ol
    0.06
     rustic
    0.06
     mutated
    0.06
     나타
    0.06
     PropTypes
    0.06
     �
    0.06
    Act Density 0.010%

    No Known Activations