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

    Neuronpedia

    INDEX
    Explanations

    birth

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.09
     Eagle
    -0.08
     والمت
    -0.08
     comprador
    -0.08
     Coff
    -0.08
     facendo
    -0.08
    鹰
    -0.08
     acus
    -0.07
     inciso
    -0.07
     cant
    -0.07
    POSITIVE LOGITS
     spur
    0.09
    予定
    0.08
     జరిగిన
    0.08
     fantasies
    0.07
     propaganda
    0.07
    zeit
    0.07
     ನಡೆದ
    0.07
     sober
    0.07
     marg
    0.07
     individualized
    0.07
    Act Density 0.007%

    No Known Activations