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

    Neuronpedia

    INDEX
    Explanations

    Ancient libraries/translation hubs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     allergy
    -0.08
    pay
    -0.08
    usage
    -0.08
     liability
    -0.07
     microwave
    -0.07
    ilis
    -0.07
     earbuds
    -0.07
    _DS
    -0.07
     nier
    -0.07
    (pay
    -0.07
    POSITIVE LOGITS
     sayesinde
    0.11
     Dankzij
    0.11
     العلماء
    0.11
     благодаря
    0.10
     flourishing
    0.10
     fostering
    0.10
     renowned
    0.10
     UNESCO
    0.10
     filóso
    0.10
     famously
    0.09
    Act Density 0.009%

    No Known Activations