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

    Neuronpedia

    INDEX
    Explanations

    Foreign languages

    np_max-act · gemini-2.0-flash

    This neuron detects tokens in Indic scripts (e.g. Bengali characters and diacritics).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     utilities
    -0.08
     vra
    -0.07
     Speed
    -0.07
     Waste
    -0.07
     specialties
    -0.07
    spy
    -0.07
     fu
    -0.07
    icus
    -0.06
    nio
    -0.06
     violence
    -0.06
    POSITIVE LOGITS
    ademic
    0.06
    LOGIN
    0.06
    ensely
    0.06
     assertThat
    0.06
    .getRow
    0.06
     banc
    0.06
    (propertyName
    0.06
     instal
    0.06
    .setContent
    0.06
     moden
    0.06
    Act Density 0.029%

    No Known Activations