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

    Neuronpedia

    INDEX
    Explanations

    following next or specific nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Má
    0.50
    dataFormat
    0.49
    美丽的
    0.48
    TabIndex
    0.47
    Historia
    0.47
    MouseEnter
    0.47
     Анаста
    0.47
     Música
    0.46
    Astronom
    0.46
    JSONArray
    0.46
    POSITIVE LOGITS
     )
    0.58
     ),
    0.53
     &
    0.47
     trung
    0.46
     b
    0.46
     hill
    0.46
     oke
    0.44
    ,
    0.44
     wang
    0.42
     Value
    0.42
    Act Density 0.003%

    No Known Activations