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

    Neuronpedia

    INDEX
    Explanations

    active

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     PRES
    -0.07
     얼
    -0.07
     nem
    -0.07
     home
    -0.06
    olis
    -0.06
    ิศ
    -0.06
     disemb
    -0.06
     Sens
    -0.06
     assassin
    -0.06
     Jennings
    -0.06
    POSITIVE LOGITS
    ?>
↵
    0.07
     제품
    0.07
    -ı
    0.06
     amatør
    0.06
    reira
    0.06
     halinde
    0.06
     smoker
    0.06
    .NODE
    0.06
     sunt
    0.06
     zprávy
    0.06
    Act Density 0.003%

    No Known Activations