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

    Neuronpedia

    INDEX
    Explanations

    code commands or fixed phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    smtp
    0.78
     voluptate
    0.77
    没有任何
    0.68
     FileInputStream
    0.68
    所有的
    0.68
    ButtonClicked
    0.66
     всеми
    0.65
    BeerItem
    0.65
     пусто
    0.64
     месе
    0.64
    POSITIVE LOGITS
    spo
    0.78
     elsewhere
    0.72
     করেও
    0.72
     markings
    0.69
     Design
    0.69
     tricks
    0.68
     Partner
    0.68
    的朋友
    0.68
    ंकन
    0.67
    iligung
    0.67
    Act Density 0.362%

    No Known Activations