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

    Neuronpedia

    INDEX
    Explanations

    Positive state/sentiment

    np_max-act · gemini-2.0-flash

    The neuron fires on descriptive words carrying positive or evaluative sentiment (i.e. subjective adjectives and adverbs).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    转
    -0.08
    lc
    -0.08
    าข
    -0.07
     ferry
    -0.07
    _TOTAL
    -0.07
     شرح
    -0.07
     Ice
    -0.07
     �
    -0.07
     Marina
    -0.07
     globalization
    -0.07
    POSITIVE LOGITS
    ());↵↵↵
    0.07
    );↵↵↵
    0.07
    ']↵↵↵
    0.06
    /commons
    0.06
    '↵↵↵
    0.06
     );↵↵↵
    0.06
     UNIVERS
    0.06
     될
    0.06
     verbally
    0.06
     ]↵↵↵
    0.06
    Act Density 0.182%

    No Known Activations