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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash

    code structure and definitions in programming or technical documents.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     рівень
    -0.07
     Elena
    -0.07
    ,address
    -0.06
     destinations
    -0.06
    edge
    -0.06
    аліз
    -0.06
    Luckily
    -0.06
     Peanut
    -0.06
    tti
    -0.06
    inan
    -0.06
    POSITIVE LOGITS
    训
    0.08
    خل
    0.06
     hus
    0.06
    .setTextColor
    0.06
    maj
    0.06
     Predator
    0.06
    .kafka
    0.06
     أبي
    0.06
    Prim
    0.06
     Hitch
    0.06
    Act Density 0.002%

    No Known Activations