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

    Neuronpedia

    INDEX
    Explanations

    frequency adverbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ุป
    -0.07
    _reload
    -0.06
    ワ
    -0.06
    Finish
    -0.06
    ورة
    -0.06
     περ
    -0.06
    ！↵↵
    -0.06
    リス
    -0.06
    -clean
    -0.06
     
    -0.06
    POSITIVE LOGITS
     tisk
    0.07
     indentation
    0.07
    -Key
    0.07
     handlers
    0.06
    //-----------------------------------------------------------------------------↵
    0.06
     iken
    0.06
     interpreter
    0.06
     Dere
    0.06
    ��
    0.06
     evacuation
    0.06
    Act Density 0.050%

    No Known Activations