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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mandates
    -0.08
     closely
    -0.07
    .Transactional
    -0.07
    殊
    -0.06
     giống
    -0.06
    _VALUES
    -0.06
    .Error
    -0.06
     granite
    -0.06
     Joey
    -0.06
    htable
    -0.06
    POSITIVE LOGITS
     physicist
    0.06
     Lifestyle
    0.06
    ेशन
    0.06
     ###
    0.06
     การ
    0.06
     شم
    0.06
     %
    0.06
     neck
    0.06
     (\
    0.06
    Narrated
    0.06
    Act Density 0.069%

    No Known Activations