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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dough
    -0.07
     Morg
    -0.06
     hormones
    -0.06
    Tooltip
    -0.06
     Männer
    -0.06
    ﻠ
    -0.06
    .Go
    -0.06
    daş
    -0.06
     Boat
    -0.06
     Nissan
    -0.06
    POSITIVE LOGITS
    urally
    0.07
    		
↵		
↵
    0.06
    yc
    0.06
    <Expression
    0.06
     colonial
    0.06
    transforms
    0.06
     مقدم
    0.06
    ếp
    0.06
    دي
    0.06
     LAP
    0.06
    Act Density 0.030%

    No Known Activations