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

    Neuronpedia

    INDEX
    Explanations

    props

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ानस
    -0.06
     none
    -0.06
     antic
    -0.06
    BUG
    -0.06
    dera
    -0.06
     backend
    -0.06
    출
    -0.06
    .af
    -0.06
    edu
    -0.06
    ronym
    -0.06
    POSITIVE LOGITS
    ?>↵
    0.07
    Tabla
    0.07
    Salir
    0.07
    nowrap
    0.06
     washington
    0.06
     يجب
    0.06
     prav
    0.06
     '',
↵
    0.06
    depends
    0.06
     Кат
    0.06
    Act Density 0.082%

    No Known Activations