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

    Neuronpedia

    INDEX
    Explanations

    amilies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _msgs
    -0.07
    conference
    -0.07
    ⾞
    -0.07
    env
    -0.07
     spent
    -0.06
    籍
    -0.06
     hunted
    -0.06
    zipcode
    -0.06
     Blank
    -0.06
    (SC
    -0.06
    POSITIVE LOGITS
     rail
    0.07
     hảo
    0.07
    地坪
    0.07
     bezier
    0.06
     Pepper
    0.06
     signifies
    0.06
    أوضاع
    0.06
    מדר
    0.06
    反倒
    0.06
    );
↵
    0.06
    Act Density 0.000%

    No Known Activations