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

    Neuronpedia

    INDEX
    Explanations

    their

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .cwd
    -0.07
     edilm
    -0.06
    ,obj
    -0.06
     لق
    -0.06
     сотруд
    -0.06
     ราย
    -0.06
     Mặt
    -0.06
     women
    -0.06
    iples
    -0.06
     Millennium
    -0.06
    POSITIVE LOGITS
     PWM
    0.06
    Mouse
    0.06
    PublicKey
    0.06
    idepress
    0.06
     stadiums
    0.06
    ?>
    0.06
     restless
    0.06
    jad
    0.06
     formerly
    0.06
    _COLS
    0.06
    Act Density 0.233%

    No Known Activations