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

    Neuronpedia

    INDEX
    Explanations

    law, Independence, town

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     مرک
    0.42
    鉅
    0.39
     '@
    0.37
    围绕
    0.37
    ゅう
    0.36
    apixel
    0.36
    炅
    0.36
     brand
    0.36
     squash
    0.35
     cette
    0.34
    POSITIVE LOGITS
     Army
    0.44
    𝑠
    0.41
     rusa
    0.40
     civilians
    0.40
     Civilian
    0.40
     Руси
    0.39
    <unused65>
    0.39
     EnglishChoose
    0.39
     ejército
    0.39
    business
    0.38
    Act Density 0.000%

    No Known Activations