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

    Neuronpedia

    INDEX
    Explanations

    B

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mang
    -0.09
     Surgery
    -0.09
     proseso
    -0.08
     Cardi
    -0.08
     Crit
    -0.08
     Principles
    -0.08
    ్త
    -0.07
     Claudia
    -0.07
     parto
    -0.07
     Indicator
    -0.07
    POSITIVE LOGITS
     brush
    0.09
     وعد
    0.08
    ))
↵
↵
    0.08
     lifetime
    0.08
     brushes
    0.08
     جاه
    0.08
     обладают
    0.08
     bafite
    0.08
    ])
↵
    0.08
    ורים
    0.07
    Act Density 0.000%

    No Known Activations