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

    Neuronpedia

    INDEX
    Explanations

    developer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    밑
    -0.07
     z
    -0.07
    一个多月
    -0.07
    两年
    -0.07
     علين
    -0.07
     נתונים
    -0.06
     arriv
    -0.06
     known
    -0.06
    צא
    -0.06
    _RATE
    -0.06
    POSITIVE LOGITS
     developers
    0.07
     elic
    0.07
    (region
    0.07
    >',↵
    0.07
    (util
    0.07
    				↵
    0.07
    hal
    0.07
    _reservation
    0.07
     Surrey
    0.07
     brides
    0.07
    Act Density 0.011%

    No Known Activations