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

    Neuronpedia

    INDEX
    Explanations

    communication cues and language

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    \
    0.66
     plutonium
    0.50
     potassium
    0.50
    asem
    0.47
    .
    0.47
    Scan
    0.47
     সীম
    0.47
     curcumin
    0.46
     কূট
    0.46
    ingan
    0.46
    POSITIVE LOGITS
    ﻕ
    0.50
     प्रा
    0.49
    ंटा
    0.47
     Приступљено
    0.46
     தவற
    0.46
    inters
    0.46
     Marlborough
    0.45
    ාල
    0.45
    鲶
    0.44
    ↵
    0.43
    Act Density 0.045%

    No Known Activations