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

    Neuronpedia

    INDEX
    Explanations

    coding languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     iris
    -0.07
    .selector
    -0.07
    confirmation
    -0.07
    มอ
    -0.06
    (dataSource
    -0.06
     Hayward
    -0.06
     Germany
    -0.06
     UserRole
    -0.06
    irket
    -0.06
     close
    -0.06
    POSITIVE LOGITS
     *,
    0.07
     SHA
    0.07
     distinction
    0.07
     цього
    0.06
     MIL
    0.06
    431
    0.06
     ><
    0.06
    )},
    0.06
     poder
    0.06
     weiß
    0.06
    Act Density 0.057%

    No Known Activations