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

    Neuronpedia

    INDEX
    Explanations

    scientific studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    消费
    -0.07
    .xz
    -0.06
     Geo
    -0.06
    _AUTH
    -0.06
    $date
    -0.06
     production
    -0.06
     agriculture
    -0.06
     Savior
    -0.06
    AGIC
    -0.06
     executive
    -0.06
    POSITIVE LOGITS
     即
    0.07
     cucumber
    0.07
    retorno
    0.07
     pronunciation
    0.07
    伴
    0.07
     момент
    0.06
    ımızda
    0.06
    Contacts
    0.06
     unaware
    0.06
     datové
    0.06
    Act Density 0.002%

    No Known Activations