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

    Neuronpedia

    INDEX
    Explanations

    mango, melon

    np_max-act · gemini-2.0-flash

    This neuron activates on occurrences of “melon” (e.g., “watermelon” and related melon terms).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     trouble
    -0.06
     Wire
    -0.06
    /ubuntu
    -0.06
     d
    -0.06
    .dictionary
    -0.06
    тою
    -0.06
    .track
    -0.06
    .order
    -0.06
    (Time
    -0.06
    اتر
    -0.06
    POSITIVE LOGITS
     yang
    0.07
     pineapple
    0.07
    AC
    0.07
    endoza
    0.07
     nav
    0.06
    aab
    0.06
     backbone
    0.06
     estas
    0.06
     ingestion
    0.06
     peach
    0.06
    Act Density 0.004%

    No Known Activations