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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    attice
    -0.06
    系
    -0.06
    الى
    -0.06
     Sanayi
    -0.06
    胎
    -0.06
    .Cell
    -0.06
     شناخته
    -0.06
    Ζ
    -0.06
    .Platform
    -0.05
     constrained
    -0.05
    POSITIVE LOGITS
     moss
    0.06
    .paths
    0.06
     filtration
    0.06
     aftermath
    0.06
    曼
    0.06
    ковод
    0.06
    emás
    0.06
     [];
↵
    0.06
     Toll
    0.06
     refr
    0.06
    Act Density 0.003%

    No Known Activations