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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (normal
    -0.07
     cheer
    -0.07
     Spicer
    -0.06
     Reid
    -0.06
    oslav
    -0.06
     приводит
    -0.06
     Witch
    -0.06
     institutions
    -0.06
     glorious
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    üme
    0.07
     øns
    0.07
    dropIfExists
    0.07
    .]↵↵
    0.06
     resale
    0.06
    _KeyPress
    0.06
     인천
    0.06
    (__('
    0.06
     listed
    0.06
     Alternate
    0.06
    Act Density 0.102%

    No Known Activations