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

    Neuronpedia

    INDEX
    Explanations

    comp words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (track
    -0.07
    彦
    -0.07
    Facade
    -0.07
    radi
    -0.06
    ampus
    -0.06
     rainy
    -0.06
     ساعت
    -0.06
     Katz
    -0.06
    ,､
    -0.06
    roit
    -0.06
    POSITIVE LOGITS
    	pstmt
    0.07
    ("..
    0.07
    .dataSource
    0.06
     �
    0.06
     hướng
    0.06
     restaurants
    0.06
    कन
    0.06
     onOptionsItemSelected
    0.06
     Redistributions
    0.06
    .shutdown
    0.06
    Act Density 0.004%

    No Known Activations