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

    Neuronpedia

    INDEX
    Explanations

    Programming errors/code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     acidity
    -0.08
    .car
    -0.07
     ".",
    -0.07
    👙
    -0.07
    يران
    -0.07
    Interest
    -0.07
    סייע
    -0.07
    �
    -0.07
    icious
    -0.07
    ."</
    -0.06
    POSITIVE LOGITS
    expectException
    0.06
    前后
    0.06
     kB
    0.06
    试验
    0.06
     Compar
    0.06
    ab
    0.06
    Models
    0.06
    完成
    0.06
    -C
    0.06
     Workout
    0.06
    Act Density 0.066%

    No Known Activations