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

    Neuronpedia

    INDEX
    Explanations

    Code/data snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     translateY
    -0.07
     lithium
    -0.07
    (DateTime
    -0.07
     Bren
    -0.06
     languages
    -0.06
     svém
    -0.06
    .Publish
    -0.06
    .Pointer
    -0.06
    aciente
    -0.06
     Certif
    -0.06
    POSITIVE LOGITS
     masturbation
    0.07
    ião
    0.07
     tester
    0.06
    00
    0.06
     retrieved
    0.06
    	ref
    0.06
    lena
    0.06
     beasts
    0.06
     кли
    0.06
     مدل
    0.06
    Act Density 0.072%

    No Known Activations