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

    Neuronpedia

    INDEX
    Explanations

    cinema

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     meals
    -0.08
     flowers
    -0.07
    Cleaning
    -0.07
     Pennsylvania
    -0.06
     IMPLIED
    -0.06
    Rad
    -0.06
    Persona
    -0.06
    ้องพ
    -0.06
    Math
    -0.06
     مالی
    -0.06
    POSITIVE LOGITS
     Film
    0.08
    ogra
    0.07
    .kafka
    0.07
     intertw
    0.07
    ิทธ
    0.07
     genu
    0.06
     Evaluate
    0.06
     कथ
    0.06
    特色
    0.06
     tension
    0.06
    Act Density 0.063%

    No Known Activations