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

    Neuronpedia

    INDEX
    Explanations

    companies heavily rely on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     উদ্দেশে
    0.95
     estadounidense
    0.78
    แน่น
    0.78
     WorldCat
    0.76
    ay
    0.74
    ссий
    0.71
     consideración
    0.69
     американский
    0.68
     reass
    0.68
     inspiración
    0.68
    POSITIVE LOGITS
    𝙩
    1.23
    𝙨
    1.20
     Differences
    1.17
    ема
    1.15
    𝙣
    1.15
    Particles
    1.14
     salaries
    1.12
    𝚝
    1.10
     yǒu
    1.10
    𝙪
    1.09
    Act Density 0.000%

    No Known Activations