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

    Neuronpedia

    INDEX
    Explanations

    master

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Token
    -0.08
     Actors
    -0.08
    assembler
    -0.07
     Az
    -0.07
    <Assembly
    -0.07
     atores
    -0.07
     actores
    -0.07
    ulem
    -0.07
    全民
    -0.07
     interpreter
    -0.07
    POSITIVE LOGITS
     المركز
    0.08
     холодиль
    0.08
     gezin
    0.08
     спаль
    0.08
     gyr
    0.08
    �
    0.08
     cooling
    0.08
     �
    0.08
     overheating
    0.08
     depression
    0.08
    Act Density 0.003%

    No Known Activations