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

    Neuronpedia

    INDEX
    Explanations

    ad

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     brushes
    -0.07
     объект
    -0.06
    role
    -0.06
     spree
    -0.06
     business
    -0.06
     crochet
    -0.06
    igrated
    -0.06
    (IService
    -0.06
     contacts
    -0.06
     groups
    -0.06
    POSITIVE LOGITS
    packet
    0.07
    도가
    0.06
     FO
    0.06
     Jamaica
    0.06
    _DUMP
    0.06
    ्प
    0.06
     whatsoever
    0.06
    홈
    0.06
    ::::|
    0.06
    _pa
    0.06
    Act Density 0.000%

    No Known Activations