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

    Neuronpedia

    INDEX
    Explanations

    table separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Doctrine
    0.63
    مت
    0.61
    每
    0.59
    긍
    0.58
     Markers
    0.58
    Manage
    0.56
    ग्रेड
    0.56
    全
    0.56
     стандарт
    0.56
    Authorization
    0.56
    POSITIVE LOGITS
    usingCamera
    0.65
    oba
    0.64
    ube
    0.63
     swamps
    0.62
    burn
    0.60
     vant
    0.58
    avez
    0.58
    rama
    0.58
    𝑜
    0.58
    pture
    0.58
    Act Density 0.011%

    No Known Activations