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

    Neuronpedia

    INDEX
    Explanations

    SAT

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.08
     sect
    -0.07
    欢迎大家
    -0.07
     BorderRadius
    -0.07
     parsers
    -0.07
    ⼤
    -0.07
    ysts
    -0.07
     avid
    -0.06
    �
    -0.06
     Adjustment
    -0.06
    POSITIVE LOGITS
     ";↵
    0.07
    ']:↵
    0.07
    )";↵
    0.07
    쒔
    0.07
     '|
    0.07
    muş
    0.07
    >'↵
    0.07
     특정
    0.06
    建立了
    0.06
    _ORIGIN
    0.06
    Act Density 0.005%

    No Known Activations