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

    Neuronpedia

    INDEX
    Explanations

    punctuation and saying

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Investors
    -0.07
    Remember
    -0.07
     SUPPORT
    -0.07
    OF
    -0.06
    	Integer
    -0.06
     parece
    -0.06
    'est
    -0.06
     個
    -0.06
    patches
    -0.06
     pregnant
    -0.06
    POSITIVE LOGITS
    :
↵
    0.08
    0.06
    ункт
    0.06
     analogy
    0.06
    posted
    0.06
    حث
    0.06
    fun
    0.06
     کرد
    0.06
    尿
    0.06
    bundle
    0.06
    Act Density 0.006%

    No Known Activations