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

    Neuronpedia

    INDEX
    Explanations

    types and examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     traités
    0.44
     tratados
    0.43
     avevo
    0.43
     gliding
    0.42
     estudar
    0.41
     bushes
    0.40
     fisi
    0.40
    ImageLayout
    0.40
     preprocessing
    0.40
     což
    0.40
    POSITIVE LOGITS
    jenis
    0.45
    ↵↵
    0.41
    主な
    0.38
    主演
    0.36
    genre
    0.35
    人数
    0.33
    となり
    0.32
    "/>
    0.32
    对自己
    0.31
    ​
    0.31
    Act Density 0.075%

    No Known Activations