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

    Neuronpedia

    INDEX
    Explanations

    by + [word]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ক
    2.14
    promises
    2.13
    ab
    2.09
    น้อง
    2.08
    的所有
    2.06
    मित्व
    2.05
     extrémités
    2.05
    ።
    2.00
    น้อย
    1.98
     diejenigen
    1.98
    POSITIVE LOGITS
    zantine
    3.33
    ه
    2.61
     virtue
    2.55
    ์
    2.55
    ી
    2.28
     wayside
    2.09
    i
    2.05
    ați
    1.91
     middel
    1.87
    🅐
    1.87
    Act Density 0.237%

    No Known Activations