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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Reggie
    -0.08
    追逐
    -0.07
    ,request
    -0.07
    configs
    -0.07
     Watts
    -0.07
    .setToolTip
    -0.07
    .putString
    -0.07
     Dave
    -0.07
     Sutton
    -0.07
     чуть
    -0.07
    POSITIVE LOGITS
     realized
    0.07
    _fl
    0.07
     Jeep
    0.06
     ##
    0.06
    月中旬
    0.06
    쪄
    0.06
     Depot
    0.06
     heter
    0.06
    (Program
    0.06
    헸
    0.06
    Act Density 0.000%

    No Known Activations