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

    Neuronpedia

    INDEX
    Explanations

    deformity, defect, lost, adapted

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ます
    1.32
    اً
    1.14
    ю
    1.06
    ‌ترین
    1.05
    ize
    1.04
     ще
    1.00
    ات
    0.99
    у
    0.98
     무엇
    0.94
    ,\"
    0.93
    POSITIVE LOGITS
     deformity
    1.32
     cardiop
    1.30
     निपटने
    1.21
     braking
    1.19
     concomit
    1.17
     conspiring
    1.16
     concerted
    1.16
     pristup
    1.16
    defect
    1.16
    codon
    1.16
    Act Density 0.000%

    No Known Activations