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

    Neuronpedia

    INDEX
    Explanations

    code debugging output

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    上级
    -0.07
    鹮
    -0.07
    席执行
    -0.06
    当然
    -0.06
    NSDictionary
    -0.06
     hatte
    -0.06
    儘
    -0.06
    😷
    -0.06
    论证
    -0.06
    _dict
    -0.06
    POSITIVE LOGITS
    Split
    0.08
    modules
    0.08
     plank
    0.08
     spaced
    0.07
     realm
    0.07
    Answers
    0.07
    (fileName
    0.07
     troubles
    0.07
    Gravity
    0.07
    .unlock
    0.07
    Act Density 0.028%

    No Known Activations