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

    Neuronpedia

    INDEX
    Explanations

    history, existence, life, mind

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mensaje
    0.50
    Entertainment
    0.48
    filePath
    0.47
     העולם
    0.47
    Focus
    0.46
    内容
    0.46
    Siempre
    0.46
    ル
    0.45
    뿍
    0.45
     গল্প
    0.45
    POSITIVE LOGITS
     a
    0.48
     this
    0.47
     remainder
    0.47
     repeal
    0.47
     ETH
    0.45
     somebody
    0.44
     DER
    0.44
     certain
    0.44
     breech
    0.43
     repeater
    0.43
    Act Density 0.006%

    No Known Activations