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

    Neuronpedia

    INDEX
    Explanations

    describing qualities or relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     อุ
    0.55
     지하
    0.49
     جنگ
    0.48
     보호
    0.48
    aaS
    0.47
     ғ
    0.47
     آموزش
    0.47
     작
    0.45
     қа
    0.45
     기능
    0.45
    POSITIVE LOGITS
     chipset
    0.53
     paralysis
    0.47
     costing
    0.47
     adjective
    0.46
     ratings
    0.46
     losing
    0.46
     annoyed
    0.46
     adjectives
    0.45
     Courtney
    0.45
     Burt
    0.45
    Act Density 0.016%

    No Known Activations