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

    Neuronpedia

    INDEX
    Explanations

    activation and negation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rationalize
    1.02
     Всё
    0.95
     Obj
    0.93
     underpin
    0.91
     alphanumeric
    0.90
     personalise
    0.89
     gering
    0.89
     decentralized
    0.88
     dropdown
    0.88
    ం
    0.87
    POSITIVE LOGITS
    ları
    1.13
    гі
    0.98
    ından
    0.96
    ва
    0.96
    es
    0.95
    š
    0.95
    ς
    0.93
    şı
    0.92
    στό
    0.89
    ř
    0.88
    Act Density 0.000%

    No Known Activations