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

    Neuronpedia

    INDEX
    Explanations

    emojis and uncommon unicode

    np_max-act · gemini-2.0-flash

    The neuron responds to emoji and other non-alphanumeric symbol tokens.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Tet
    -0.08
     February
    -0.07
     Little
    -0.07
    मत
    -0.07
     Bay
    -0.07
    lest
    -0.06
     August
    -0.06
     rost
    -0.06
    .file
    -0.06
    attering
    -0.06
    POSITIVE LOGITS
    bbox
    0.07
     onload
    0.07
    ‍
    0.06
     pos
    0.06
    Iso
    0.06
     يجب
    0.06
    亲
    0.06
    (inputStream
    0.06
    .ImageIcon
    0.06
     Danny
    0.06
    Act Density 0.001%

    No Known Activations