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

    Neuronpedia

    INDEX
    Explanations

    audio

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     whose
    -0.07
     اث
    -0.06
     해
    -0.06
    講
    -0.06
    REGISTER
    -0.06
     DAMAGES
    -0.06
     طر
    -0.06
     moth
    -0.06
     lingerie
    -0.06
    ών
    -0.06
    POSITIVE LOGITS
    "])↵↵
    0.08
    lédl
    0.08
    ')↵↵
    0.07
       ↵↵
    0.07
    IDADE
    0.07
     inhab
    0.07
      ↵↵
    0.07
        ↵↵
    0.07
           ↵↵
    0.06
    ())↵↵
    0.06
    Act Density 0.399%

    No Known Activations