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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tricks
    -0.07
     부산
    -0.06
     BJ
    -0.06
     Append
    -0.06
     revealing
    -0.06
    лися
    -0.06
     clich
    -0.06
     Submission
    -0.06
    release
    -0.06
     lived
    -0.06
    POSITIVE LOGITS
     انگ
    0.07
    λογία
    0.07
    过
    0.06
    .met
    0.06
     �
    0.06
    .addMouseListener
    0.06
     กร
    0.06
     AdapterView
    0.06
    \Exceptions
    0.06
     همان
    0.06
    Act Density 0.053%

    No Known Activations