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

    Neuronpedia

    INDEX
    Explanations

    file paths, code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     creo
    -0.07
     Anderson
    -0.07
     Wilson
    -0.06
    450
    -0.06
     ----------------------------------------------------------------------------
    -0.06
     próximo
    -0.06
     "-";↵
    -0.06
     origen
    -0.06
    Wilson
    -0.06
    271
    -0.06
    POSITIVE LOGITS
     thậm
    0.08
    ↵            
↵
    0.07
    (components
    0.07
     Pf
    0.07
            
↵        
↵
    0.07
     overriding
    0.06
    TeX
    0.06
     exceptions
    0.06
    وص
    0.06
    .tabPage
    0.06
    Act Density 0.014%

    No Known Activations