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

    Neuronpedia

    INDEX
    Explanations

    improvement through practice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    requests
    -0.07
     Gordon
    -0.07
    ads
    -0.06
    892
    -0.06
     drv
    -0.06
    ad
    -0.06
     α
    -0.06
     enqueue
    -0.06
     Nancy
    -0.06
     authoritative
    -0.06
    POSITIVE LOGITS
     BusinessException
    0.06
     selbst
    0.06
    pción
    0.06
    ัล
    0.06
    iously
    0.06
     offence
    0.06
     isempty
    0.06
     Collabor
    0.06
     πριν
    0.06
    tility
    0.06
    Act Density 0.041%

    No Known Activations