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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    izzas
    -0.07
     báo
    -0.07
    handleRequest
    -0.07
    -0.06
    (pages
    -0.06
    (team
    -0.06
     };
↵
    -0.06
    “A
    -0.06
    ись
    -0.06
    	fwrite
    -0.06
    POSITIVE LOGITS
    ху
    0.07
     hosted
    0.07
     REQUIRED
    0.07
    โพ
    0.06
     Zusammen
    0.06
     subtype
    0.06
     unterschied
    0.06
    ancies
    0.06
    /demo
    0.06
    古
    0.06
    Act Density 0.015%

    No Known Activations