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

    Neuronpedia

    INDEX
    Explanations

    multilingual word fragments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    入り
    0.39
     जाहीर
    0.39
    Comprehensive
    0.39
     дово
    0.37
    CONF
    0.37
     发表于
    0.37
    Alle
    0.37
    Luca
    0.37
    <0xE2>
    0.36
    скага
    0.36
    POSITIVE LOGITS
    uminum
    0.43
    るとき
    0.40
    istice
    0.40
    ración
    0.39
    ouville
    0.39
     cert
    0.38
    renamiento
    0.38
     charter
    0.38
     কথাও
    0.38
    圈
    0.38
    Act Density 0.008%

    No Known Activations