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

    Neuronpedia

    INDEX
    Explanations

    small decorative pieces

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of “sequin” and its variants (e.g. sequined, sequins).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     тебя
    -0.07
     То
    -0.07
     Quality
    -0.06
     слід
    -0.06
     Ivan
    -0.06
     sabah
    -0.06
     gentleman
    -0.06
     concrete
    -0.06
     infants
    -0.06
     Redirect
    -0.06
    POSITIVE LOGITS
    št
    0.06
    ذه
    0.06
     Kew
    0.06
     qualifier
    0.06
    :indexPath
    0.06
    (*
    0.06
    .slot
    0.06
    WARDED
    0.06
    _TOGGLE
    0.06
    Tutorial
    0.06
    Act Density 0.086%

    No Known Activations