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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    QtCore
    -0.07
    @example
    -0.07
     말
    -0.07
     Castle
    -0.06
    PX
    -0.06
    ถนน
    -0.06
    .forward
    -0.06
     positions
    -0.06
     para
    -0.06
     голос
    -0.06
    POSITIVE LOGITS
     AGAIN
    0.07
     Tacoma
    0.07
     přiroz
    0.07
     ResponseEntity
    0.07
     flatt
    0.06
    。不
    0.06
     Влади
    0.06
     Marseille
    0.06
    .lbl
    0.06
    uez
    0.06
    Act Density 0.022%

    No Known Activations