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

    Neuronpedia

    INDEX
    Explanations

    Batman

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    jours
    -0.08
    嘉
    -0.07
     pra
    -0.07
     evt
    -0.07
    相信
    -0.07
     gele
    -0.06
    زل
    -0.06
     agregar
    -0.06
     NBC
    -0.06
     vysoké
    -0.06
    POSITIVE LOGITS
     Superman
    0.09
     Grades
    0.07
    [level
    0.06
     MU
    0.06
     Boo
    0.06
    924
    0.06
    SPACE
    0.06
    Shapes
    0.06
     Rover
    0.06
    ΙΑΣ
    0.06
    Act Density 0.006%

    No Known Activations