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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    助手
    -0.08
    title
    -0.07
    騰
    -0.07
     başına
    -0.07
    Chapter
    -0.07
     Marie
    -0.07
     beau
    -0.07
     BSON
    -0.06
     comes
    -0.06
     purchased
    -0.06
    POSITIVE LOGITS
    _Framework
    0.08
    ()):↵
    0.07
    拦
    0.07
    Severity
    0.07
    .localization
    0.07
    从中
    0.07
    -ag
    0.07
     GRID
    0.06
    與
    0.06
     amort
    0.06
    Act Density 0.031%

    No Known Activations