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

    Neuronpedia

    INDEX
    Explanations

    Fitness Classes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     monopoly
    -0.10
     Acad
    -0.08
    perm
    -0.08
    enspiel
    -0.07
     nepot
    -0.07
     Akadem
    -0.07
    /ioutil
    -0.07
     مون
    -0.07
     যোগাযোগ
    -0.07
     reis
    -0.07
    POSITIVE LOGITS
     workouts
    0.10
     abwechslungs
    0.10
     workout
    0.09
    Workout
    0.09
     Workout
    0.09
     Mix
    0.09
     sessions
    0.09
     mix
    0.09
     جلسه
    0.09
    エ
    0.08
    Act Density 0.027%

    No Known Activations