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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     TVs
    -0.07
     pirate
    -0.06
    gap
    -0.06
     compassionate
    -0.06
    有关
    -0.06
     JSON
    -0.06
     UUID
    -0.06
    ethical
    -0.06
     CLEAN
    -0.06
    mployee
    -0.06
    POSITIVE LOGITS
     compliments
    0.07
    <footer
    0.06
    ）（
    0.06
    izzare
    0.06
    食品
    0.06
     شرایط
    0.06
    ід
    0.06
     popularity
    0.06
     employers
    0.06
    級
    0.06
    Act Density 0.039%

    No Known Activations