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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating progress or improvement in performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    improvement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DatabaseError
    -0.36
     geï
    -0.36
    ждён
    -0.35
     unieke
    -0.34
    nezeu
    -0.33
    aronder
    -0.33
     unique
    -0.32
    "}")
    -0.32
     rød
    -0.32
    rijfs
    -0.32
    POSITIVE LOGITS
    windowFixed
    0.64
    WebElementEntity
    0.59
    uggest
    0.57
     restored
    0.53
    AnimationsModule
    0.53
    improved
    0.52
    amélioration
    0.50
     redis
    0.50
     Reborn
    0.50
     Comeback
    0.49
    Act Density 0.078%

    No Known Activations