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

    Neuronpedia

    INDEX
    Explanations

    code, XML, and indentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    あります
    -0.07
    _INITIAL
    -0.07
     launching
    -0.06
    \$
    -0.06
    ParseException
    -0.06
     }},↵
    -0.06
    إبداع
    -0.06
     Wichita
    -0.06
    各自
    -0.06
    先生
    -0.06
    POSITIVE LOGITS
    因为他们
    0.07
     água
    0.07
    ocup
    0.07
    곱
    0.07
    上前
    0.07
     waves
    0.07
    (compare
    0.07
    储量
    0.07
    ʷ
    0.07
    ículo
    0.07
    Act Density 0.061%

    No Known Activations