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

    Neuronpedia

    INDEX
    Explanations

    ware

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -oriented
    -0.07
    ざ
    -0.06
     Governance
    -0.06
    ryptography
    -0.06
     suce
    -0.06
     justification
    -0.06
    abama
    -0.06
     focuses
    -0.06
     życ
    -0.06
     adorned
    -0.06
    POSITIVE LOGITS
        
↵    
↵
    0.07
    graduate
    0.06
        
↵
↵
    0.06
     redraw
    0.06
     OMAP
    0.06
     prescribing
    0.06
    breaking
    0.06
    uelles
    0.06
    PTR
    0.06
    MainWindow
    0.06
    Act Density 0.014%

    No Known Activations