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

    Neuronpedia

    INDEX
    Explanations

    most, largest

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pir
    -0.07
    ,S
    -0.07
     whose
    -0.07
     sail
    -0.07
     Rus
    -0.06
     its
    -0.06
    Rol
    -0.06
    ुत
    -0.06
    haus
    -0.06
     plage
    -0.06
    POSITIVE LOGITS
     Colour
    0.07
     Albuquerque
    0.06
    ический
    0.06
    ض
    0.06
    ampler
    0.06
     curb
    0.06
    IOS
    0.06
    UserID
    0.06
    .Roll
    0.06
    next
    0.06
    Act Density 0.008%

    No Known Activations