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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    The neuron fires on words that evoke the “small fish in a big ocean” size‐contrast imagery—especially the adjectives “small” and “big” (including repeated “big, big”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Compiler
    -0.07
     culture
    -0.07
    �인
    -0.07
     MONEY
    -0.07
    -preview
    -0.07
    -ap
    -0.07
    utility
    -0.06
     ordered
    -0.06
     cultures
    -0.06
     Grain
    -0.06
    POSITIVE LOGITS
     consulta
    0.07
     Gunn
    0.06
     baz
    0.06
     Bob
    0.06
    runs
    0.06
    .responseText
    0.06
     дых
    0.06
     isso
    0.06
     ↓
    0.06
     Entities
    0.06
    Act Density 0.498%

    No Known Activations