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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     apresentação
    -0.09
    Gov
    -0.09
     презента
    -0.09
     presentación
    -0.08
     presentatie
    -0.08
     proud
    -0.07
     nó
    -0.07
    Presentation
    -0.07
     presentations
    -0.07
     homeowners
    -0.07
    POSITIVE LOGITS
     inhab
    0.08
     computes
    0.07
    -De
    0.07
     �
    0.07
     Roh
    0.07
    (all
    0.07
     Ehr
    0.07
     આપે
    0.07
    乘
    0.07
     unravel
    0.07
    Act Density 0.058%

    No Known Activations