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

    Neuronpedia

    INDEX
    Explanations

    dog adoption

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Stat
    -0.07
    소개
    -0.07
    归
    -0.06
     amendments
    -0.06
     bugs
    -0.06
     lé
    -0.06
     Complexity
    -0.06
     assurances
    -0.06
     QA
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     desktop
    0.07
     pcl
    0.07
     falsehood
    0.06
     serving
    0.06
    _kernel
    0.06
    .Forms
    0.06
    (parse
    0.06
    (tf
    0.06
    (predict
    0.06
    νονται
    0.06
    Act Density 0.038%

    No Known Activations