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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating judgment or emotional valuation

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

    chance or possibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     voces
    -0.35
     السابق
    -0.32
     OnInit
    -0.31
     tradu
    -0.31
    funcionario
    -0.31
    requent
    -0.30
    herme
    -0.30
    QMetaType
    -0.30
    对其
    -0.30
     letti
    -0.30
    POSITIVE LOGITS
    httphttps
    0.83
     bahwa
    0.63
    RTSC
    0.61
     that
    0.60
     désolés
    0.58
     cherchés
    0.57
    addCriterion
    0.57
    ImageContext
    0.57
     NgModule
    0.55
    IVEREF
    0.54
    Act Density 0.425%

    No Known Activations